DESC:FORM 2 THE PATENTS ACT, 1970 (39 of 1970) & THE PATENT RULES, 2003 COMPLETE SPECIFICATION (See Section 10 and Rule 13) Title of invention: METHOD AND SYSTEM FOR PERFORMING NEGOTIATION TASK USING REINFORCEMENT LEARNING AGENTS Applicant Tata Consultancy Services Limited A company Incorporated in India under the Companies Act, 1956 Having address: Nirmal Building, 9th floor, Nariman point, Mumbai 400021, Maharashtra, India The following specification particularly describes the invention and the manner in which it is to be performed. CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY The present application claims priority from Indian patent application no. (201821026198), filed on July 13, 2018 the complete disclosure of which, in its entirety is herein incorporated by reference. TECHNICAL FIELD The disclosure herein generally relates for automation of negotiation task, and, more particularly, to a method and system for performing negotiation task using reinforcement learning agents. BACKGROUND Negotiation is a complex decision making process, where agents with different goals attempt to agree on common decision of a contract agreement. Generally, complex deals frequently involve multiple parties as well as multiple negotiating interactions to reach to a contract agreement. Process to arrive at consensus on contents of the contract agreement is often expensive and time consuming task due to the negotiation terms and the negotiation parties involved. Traditional negotiation methods involve face to face negotiation requiring manual intervention. Such negotiation dialogues contain both cooperative and adversarial elements, where human agents consume time to understand, plan, and generate utterances to achieve their goal. Complete automation in the negotiation process is been a topic of interest. In an existing system attempting automation of negotiation process, agents or machine agents are trained with the reinforcement learning strategy, which makes the best use of the opponent's negotiation history. The negotiating agent makes decision of the opponent's offer type, dynamically adjusting the negotiation agent's belief of opponent in time to get more favorable and better negotiation result. However, the existing system limits in training agents with one or more different behavior patterns for contract negotiation thereby reducing time utilized by agents for performing the negotiation task and improving scalability. In another existing system, modelling deep agents for negotiation with the availability of data can be trained to imitate humans using reinforcement learning technique. These models require training data collected from one or more resource extensive different domains. However, the existing system limits in adopting reinforcement learning agents trained with different behavioral patterns as humans for contract negotiation. SUMMARY Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a system for performing negotiation task using reinforcement learning is provided. The system includes a processor, an Input/output (I/O) interface and a memory coupled to the processor is capable of executing programmed instructions stored in the processor in the memory to receive a request for performing the negotiation task by a negotiating agent implemented by the processor, between the negotiating agent and an opposition agent, to agree on an optimal contract proposal comprising a plurality of clauses from a set of clauses predefined for the negotiation task, wherein each of the negotiating agent and the opposition agent comprises a plurality of behavioral models modeled based on a reward function. Further, the negotiating agent with the plurality of behavioral models of the opposition agent negotiate one on one, to agree on a plurality of intermediate contract proposals, wherein the negotiation between each of the negotiating agent and the opposition agent is in accordance with a negotiation training procedure. Furthermore, a selector agent selects the optimal contract proposal from the plurality of intermediate contract proposals generated by performing negotiation between the negotiation agent and the opposition agent based on the negotiation training procedure, wherein the selector agent is an ensemble of the plurality of behavioral models of the negotiating agent and the opposition agent. In another aspect, a method for performing a negotiation task using reinforcement learning agents is provided. The method includes receiving a request for performing the negotiation task by a negotiating agent implemented by the processor, between the negotiating agent and an opposition agent, to agree on an optimal contract proposal comprising a plurality of clauses from a set of clauses predefined for the negotiation task, wherein each of the negotiating agent and the opposition agent comprises a plurality of behavioral models modeled based on a reward function. Further, the negotiating agent with the plurality of behavioral models of the opposition agent negotiate one on one, to agree on a plurality of intermediate contract proposals, wherein the negotiation between each of the negotiating agent and the opposition agent is in accordance with a negotiation training procedure. Furthermore, a selector agent selects the optimal contract proposal from the plurality of intermediate contract proposals generated by performing negotiation between the negotiation agent and the opposition agent based on the negotiation training procedure, wherein the selector agent is an ensemble of the plurality of behavioral models of the negotiating agent and the opposition agent. In yet another aspect, a non-transitory computer readable medium having embodied thereon a computer program for executing a method for receiving a request for performing the negotiation task by a negotiating agent implemented by the processor, between the negotiating agent and an opposition agent, to agree on an optimal contract proposal comprising a plurality of clauses from a set of clauses predefined for the negotiation task, wherein each of the negotiating agent and the opposition agent comprises a plurality of behavioral models modeled based on a reward function. Further, the negotiating agent with the plurality of behavioral models of the opposition agent negotiate one on one, to agree on a plurality of intermediate contract proposals, wherein the negotiation between each of the negotiating agent and the opposition agent is in accordance with a negotiation training procedure. Furthermore, a selector agent selects the optimal contract proposal from the plurality of intermediate contract proposals generated by performing negotiation between the negotiation agent and the opposition agent based on the negotiation training procedure, wherein the selector agent is an ensemble of the plurality of behavioral models of the negotiating agent and the opposition agent. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles: FIG. 1 illustrates a networking implementation of a negotiation system performing a negotiation task using reinforcement learning agents in accordance with an embodiment of the present disclosure. FIG. 2 illustrates an exemplary block diagram of the negotiation system performing the negotiation task using the reinforcement learning agents with another embodiment of the present disclosure. FIG. 3 is a flow diagram 300 illustrating steps of a method for performing the negotiation task reinforcement learning agents of the negotiation system of FIG. 1, in accordance with an embodiment of the present disclosure. FIG.4 illustrates an exemplary architecture of the negotiation system where reinforcement learning agents negotiate with each other on a set of clauses associated with the negotiation task negotiation interaction between the reinforcement learning agents, in accordance with an embodiment of the present disclosure. FIG.5 is an exemplary architecture of the negotiation system performing the negotiation task using the reinforcement learning agents of FIG.2, in accordance with an embodiment of the present disclosure. FIG.6 illustrates performance evaluation of the reinforcement learning agents corresponding to the plurality of behavioral models based on the frequency distribution for the sequence of actions taken for the performed negotiation task, in accordance with an embodiment of the present disclosure. FIG.7 illustrates frequency distribution values for selecting an optimal contract proposal using a selector agent for the negotiation task performed by the reinforcement learning agents, in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION OF EMBODIMENTS Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims. The embodiments herein provides a method and system for performing a negotiation task using reinforcement learning agents. The reinforcement learning agents performing the negotiation task communicate each other for negotiation using a simple communication protocol. The negotiation task herein refers to any contract agreement, private document, a license document, a legal document and /or confidential document comprising a plurality of clauses that needs to be negotiated between the two reinforcement learning agents to agree for obtaining an optimal contract proposal. The reinforcement learning agents herein includes a negotiating agent and an opposition agent and these reinforcement learning agents resides into the agents repository of the negotiation system for performing the received negotiation task. The negotiation system comprises a negotiation module 212 and an agents repository 214. The negotiation module 212 includes a negotiating agent, an opposition agent and a selector agent. The negotiation task may be obtained from one or more user involved in negotiation such that one user may be a seller and the other user may be a buyer. The negotiating agent and the opposition agent of the negotiation system initially receives the negotiation task from a user. The negotiation task comprises a plurality of clauses from a set of clauses predefined for the negotiation task. Each of the negotiating agent and the opposition agent obtains a plurality of behavioral models by playing several rounds of negotiation levels against each other. The plurality of behavioral models comprises a Selfish-Selfish (SS) model, a Selfish-Prosocial (SP) model, a Prosocial-Selfish (PS) model and a Prosocial-Prosocial (PP) model reflecting behavioral aspect of the negotiating agent paired with behavioral aspect of the opposition agent during the performance of the negotiation task. Further, the negotiating agent with the plurality of behavioral models and the opposition agent with the plurality of behavioral models are stored in the agents repository. For the purpose of performing the negotiation task, the negotiating agent with the plurality of behavioral models negotiates for each clause with the plurality of behavioral models of the opposition agent for the said clause to agree on an optimal contract proposal. Here, the negotiating agent and the opposition agent are trained with a negotiation training procedure for generating a plurality of intermediate contract proposals. Further, a selector agent associated with the negotiation system selects an intermediate contract proposal from the plurality of intermediate contract proposals based on a reward function obtained by each of the plurality of intermediate contract proposals. Here, the selector agent is an ensemble of the plurality of behavioral models of the negotiating agent and the opposition agent. Referring now to the drawings, and more particularly to FIGS. 1 through 7, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method. FIG. 1 illustrates a networking implementation of a negotiation system performing a negotiation task using a reinforcement learning agents in accordance with an embodiment of the present disclosure. The system 102, alternatively referred as negotiation system 102, is configured to receive a negotiation task from one or more user. The negotiation system 102 may be embodied in a computing device, for instance a computing device 104. Although the present disclosure is explained considering that the negotiation system 102 is implemented on a server, it may be understood that the negotiation system 102 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a cloud-based computing environment and the like. In one implementation, the negotiation system 102 may be implemented in a cloud-based environment. It will be understood that the negotiation system 102 may be accessed by multiple users through one or more user devices 104-1, 104-2... 104-N, collectively referred to as user devices 104 hereinafter, or applications residing on the user devices 104. Examples of the user devices 104 may include, but are not limited to, a portable computer, a personal digital assistant, a handheld device, a Smartphone, a Tablet Computer, a workstation and the like. The user devices 104 are communicatively coupled to the system 102 through a network 106. In an embodiment, the network 106 may be a wireless or a wired network, or a combination thereof. In an example, the network 106 can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 106 may be either a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network 108 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network 106 may interact with the negotiation system 102 through communication links. As discussed above, the negotiation system 102 may be implemented in a computing device 104, such as a hand-held device, a laptop or other portable computer, a tablet computer, a mobile phone, a PDA, a smartphone, and a desktop computer. The negotiation system 102 may also be implemented in a workstation, a mainframe computer, a server, and a network server. The components and functionalities of the negotiation system 102 are described further in detail with reference to FIG. 2 and FIG. 3. FIG. 2 illustrates an exemplary block diagram of the negotiation system performing the negotiation task using the reinforcement learning agents with another embodiment of the present disclosure. In an example embodiment, the negotiation system 102 may be embodied in, or is in direct communication with the system, for example the negotiation system 102 (FIG. 1). The negotiation system 200 includes or is otherwise in communication with one or more hardware processors such as a processor 202, at least one memory such as a memory 204, and an I/O interface 206, a negotiation module 212 and an agents repository 214. In an embodiment, the negotiation module 216 can be implemented as a standalone unit in the negotiation system 102. In another embodiment, negotiation module 212 can be implemented as a module in the memory 204. The processor 202, memory 204, and the I/O interface 206, module 208 may be coupled by a system bus such as a system bus 210 or a similar mechanism. The I/O interface 206 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The interfaces 206 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a camera device, and a printer. Further, the interfaces 206 may enable the system 102 to communicate with other devices, such as web servers and external databases. The interfaces 206 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the interfaces 206 may include one or more ports for connecting a number of computing systems with one another or to another server computer. The I/O interface 206 may include one or more ports for connecting a number of devices to one another or to another server. The hardware processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the hardware processor 202 is configured to fetch and execute computer-readable instructions stored in the memory 204. The memory 204 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 204 includes a plurality of modules 208, received, and generated by one or more of the modules 208. The modules 208 may include routines, programs, objects, components, data structures, and so on, which perform particular tasks or implement particular abstract data types. The negotiation module 212 of the system 200 can be configured to receive a contract proposal from one or more user to be negotiated with the trained negotiating agent and the opposition agent. FIG. 3 is a flow diagram 300 illustrating steps of a method for performing the negotiation task using the reinforcement learning agents of the negotiation system of FIG. 1, in accordance with an embodiment of the present disclosure. In an embodiment, the system 100 comprises one or more data storage devices or the memory 102 operatively coupled to the one or more processors 104 and is configured to store instructions for execution of steps of the method 300 by the one or more processors (alternatively referred as processor(s)) 104 in conjunction with various modules of the modules 108. The steps of the method 300 of the present disclosure will now be explained with reference to the components or blocks of the system 100 as depicted in FIG. 1 and the steps of flow diagram as depicted in FIG. 2 through 7. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously. At step 302 of the method 300, the negotiation module 212 implemented by the processor 204, is configured to receive a request by a negotiating agent, for performing the negotiation task between the negotiating agent and an opposition agent. The negotiation task brings the negotiation agent and the opposition agent to agree on an optimal contract proposal. The contract proposal comprises a plurality of clauses from a set of clauses predefined for the negotiation task. Further, each of the negotiating agent and the opposition agent comprise a plurality of behavioral models, which are modeled based on a reward function. The reinforcement learning agents includes the negotiation agent and the opposition agent associated with the negotiation module 212 of the negotiation system 102. Considering an example where the negotiation system 102 receives the negotiation task from one or more user. The received negotiation task is a contract document that needs to be negotiated between two parties wherein one of the user may be a seller and the other user may be a buyer. Performing the negotiation task using agents it is important to have a robust communication protocol. Here, the negotiating agent and the opposition agent are trained to converse using an interpretable sequence of bits. The training is done using reinforcement learning. Initially, the negotiating agent and the opposition agent are modelled as a neural network and then these two such agents are trained concurrently where they play several rounds of negotiation levels against each other and learn to coordinate with each other based on the outcome as reward function. The behavior of the negotiating agent and the opposition agent is modeled using the effective technique of varying the reward signal. With this proactive training, two agents with 4 different behavior model are obtained. The negotiating agent and the opposition agent trained in this manner indeed learn to coordinate their moves and produce context relevant outputs. At 304, the method 300 includes negotiating one on one, by the negotiating agent with the plurality of behavioral models of the opposition agent to agree on a plurality of intermediate contract proposals, wherein the negotiation between each of the negotiating agent and the opposition agent is in accordance with a negotiation training procedure. The negotiating agent obtains at time step‘t’ a plurality of state inputs, wherein the plurality of state inputs includes a utility function, an opponent offer, a previous opponent offer and an agent ID. It's Utility function U^A offer given by opponent B, S_t^B It’s previous offer, S_(t-1)^A Agent ID, I ?{0,1} Here, the received input is converted into a dense representation D_t^A as, ¦(D_t^A= =[OfferMLP([U^A,S_t^B ]),OfferMLP(U^A,S_(t-1)^A ) ), AgentLookup(I),TurnLookup(t) ------- (1) Here, OfferMLP (.) a 2-layer MLP and a AgentLookup(.) is an embedding which gives a dense representation for the agent identity and TurnLookup (.) is another embedding which encodes information in the time step ‘t’. The representation D_t^A is passed to a 2-Layer GRU (gated recurrent unit) as h_t^A = GRU (D_t^A,h_(t-1)^A) --------------------- (2) Where, h_(t-1)^Ais the hidden state generated by A at its previous turn. The number of bits to be flipped are predicted based on the action taken by the reinforcement learning agents sampling from the intermediate contract proposal p_A, p_A=Softmax(Wh_t^A ) ---------------(3) During test time selection of the action performed by the reinforcement learning agents with the highest probability. At the next time step ‘t+1’, the agent B also outputs a similar intermediate contract proposal p_B. Each of the reinforcement learning agent i=?{A,B} optimize to maximize the following object individually: L_i=¦(E@x_t~ (p_A,p_B ) ) [ ?_t¦??^((T-t) ) (r_i (x_(1….T) )-b_i ) ?]+?H[p_i ] ---------(4) Here, ‘x_t' is the action taken by an agent t, ‘?' is the discount factor, ‘T’ is the total time steps for which the negotiation lasts, ?'r?_i (x_1,….T)’ is the reward received by the negotiating agent and the opposition agent ‘i’ at the end of the negotiation which is a function of the sequence of actions 'x_t' taken by the agent from t=1 to t=T, ?'b?_i' is the baseline which is used to reduce variance, and ‘H[p_i ]’ is the entropy regularization term to ensure exploration and ? controls this degree of exploration. The parameters of the negotiating agent A and the opposition agent B are shared with each other and these parameters are updated after each episode. Each episode refers to a negotiation level between the negotiating agent A and the opposition agent B. Here, the training is executed for 5 epochs with 105 episodes in each epoch. In one embodiment, the negotiating agent for the corresponding behavioral model from the plurality of behavioral models generates, a first intermediate contract proposal utilizing the plurality of said state inputs for performing the negotiation task. Here, the first intermediate contract proposal predicts the number of bits to be flipped during the performance of the negotiation task. Further, the opposition agent obtains at next time step‘t+1’ for the corresponding behavioral from the plurality of behavioral models, a second intermediate contract proposal based on the first intermediate contract proposal obtained from the negotiating agent. Here, the second intermediate contract proposal maximizes the offer in the intermediate contract proposal for performing the negotiation task. Further, the reward is assigned for each behavior model of the intermediate contract proposal of the negotiating agent and the opposition agent based on the performed negotiation task. The reward is assigned such that a maximum reward is assigned to the negotiating agent and the opposition agent, if the generated intermediate contract proposal is optimal and a minimum reward is assigned to the negotiating agent and the opposition agent, if the generated intermediate contract proposal is not optimal. In one embodiment, the plurality of behavior models for the negotiating agent and the opposition agent of the negotiation system 102 describes the manner in which the rewards given to the reinforcement learning agents decides its behavior. The reinforcement learning agents with selfish behavior model and the agent with prosocial behavior agent represents in the following below mentioned steps, For enforcing prosocial behavior model from the plurality of behavioral models of the negotiating agent and the opposition agent, a reward is given (the number of points earned at the end of the negotiation) when the deal is optimal for each clause associated with the negotiation task. If the deal is not optimal, the negotiating agent and the opposition agent is given a reward of -0.5. This ensures that the negotiating agent and the opposition agent not only cares about its own gain/loss while learning its intermediate contract proposal but also takes into account the opponent's priorities as well. In other words, the reward here has a signal for the overall optimality. If there is no optimality signal in the reward, the negotiating agent / the opposition agent receives as a reward, whatever it earned in the negotiation, then a selfish behavior model is induced. The negotiating agent / the opposition agent then, learns to maximize its own score. Both the reinforcement learning agents such that the negotiating agent and the opposition agent receives a reward of -0.5 if the negotiation ends in a disagreement between both the agents. Here, the two agents negotiating agent and the opposition agent learn concurrently to obtain two agents with 4 different behavior model depending on the opponent is trained to behave, 1. Prosocial agent trained against a Prosocial agent (PP): The behavior PP when both the reinforcement learning agents negotiating agent and the opposition agent are trained to have a Prosocial behavior model. 2. Selfish agent trained against a Selfish agent (SS): If both the agents negotiating agent and the opposition agent are trained to be selfish for obtaining the agent Selfish agent trained against a Selfish agent. 3. Selfish agent trained against a Prosocial agent and vice-versa (SP, PS): When one agent is trained to be selfish and its opponent is trained to be prosocial, obtaining two agents represented as SP and PS respectively. At 306, the method 300 includes selecting, by a selector agent, the optimal contract proposal from the plurality of intermediate contract proposals, wherein the selector agent is an ensemble of the plurality of behavioral models of the negotiating agent and the opposition agent. Here, the plurality of contract proposals generated by the negotiating agent and the opposition agent are obtained for each behavior from the plurality of behavioral models and then am intermediate contract proposal is determined utilizing the plurality of contract proposals obtained from the plurality of behavioral models of the negotiating agent and the opposition agent and the maximum reward attained by each of the intermediate contract proposals and the frequency distribution of the negotiating agent selection sequence. For emulating human behavior, a selector agent is trained with a dynamic behavior. The trained selector agent is an ensemble of the 2 agents with 4 different behaviors modeling for selecting an appropriate behavior based on the negotiation state. Further, the negotiation agents in real world scenarios, performance are evaluated with experiments where the negotiating agent and the opposition agent play against human players. The negotiating agent and the opposition agent provides consistency in behaviors even against human players. The negotiating agent and the opposition agent are deployable in real industrial scenarios for performing negotiating on the negotiation task. The selector agent is modeled with dynamic behavior. The selfish agent outperforms always outscores its opponents. However, using such an agent leads to many disagreements if the opponent is also selfish as described in Table 2 column1. In such observation the fact that the selfish and prosocial behavior are not separable processes in negotiation. Here, the humans don't really negotiate using a fixed policy they adopt either the prosocial behavior model or the selfish behavior model. They tend to follow a mixed behavior with some degrees of both depending on the state of the negotiation process. The present disclosure models one optimal contract proposal that works well against all agents using a mixture of agents with the plurality of behavioral models. This is obtained by training another reinforcement learning gent known as selector agent to choose which of the 2 agents with 4 different behavior model for selecting the optimal contract proposal for the given state of the negotiation obtained from the negotiation task. FIG.4 illustrates an exemplary architecture of the negotiation system where reinforcement learning agents negotiate with each other on a set of clauses associated with the negotiation task negotiation interaction between the reinforcement learning agents, in accordance with an embodiment of the present disclosure. The negotiation task, alternatively referred as task, may be performed in any document comprising a plurality of clauses to agree on common terms between the negotiating parties. It will be noted that for the purpose of designing and training model for performing the negotiation task, herein the agents perform the task residing in the agents repository of the negotiation module. The model is designed such that the user obtains an optimal contract proposal from a plurality of intermediate contract proposals. In an embodiment, the negotiation system 102 includes a deep neural network (DNN) component and a rule based component. The deep neural network (DNN) Component is utilized to decide the number of bits to be flipped in the opponent's offer, wherein the deep neural network is trained through Reinforcement Learning (RL). The rule based component decides the exact bits to be flipped in a deterministic way such that flipping the bits that result in maximum increase in score. For example considering an, if the utility is [2,-6,-2;-4, 7, 3], the opponent's offer is [1, 1, 1, 0, 0, 1] and the number of bits to be flipped is 3 (decided by the neural network) that flips the second, third and fifth bit (rule based). FIG.5 is an exemplary architecture of the negotiation system performing the negotiation task using the reinforcement learning agents of FIG.2, in accordance with an embodiment of the present disclosure. In an example scenario, for performing the negotiation task on the plurality of clauses associated with the contract agreement from the negotiation environment. Here, two agents negotiating agent and the opposition agent negotiate one-on-one to agree on common terms as to which clauses need to be included or excluded from the contract agreement. Considering there are 6 clauses in the contract agreement on which the negotiating agent and the opposition agent performs the negotiation task in the negotiation environment. The value that an agent attaches to the clauses is represented by a utility function which is a vector of 6 integers between -12 and 12 (excluding 0) such that their sum is zero. There is an additional constraint that there is at least one positive and one negative value in this vector and that the sum of positives is +12 and that of the negatives is -12. This vector is represented as U= Shuffle (P?N). Here, P= [p_1,p_2,p_3…p_k] and N=[n_1,n_2,n_3…n_(6-k)], where 0