Method and system for implementing reinforcement learning agent using reinforcement learning processor

A method for implementing reinforcement learning agents using a reinforcement learning processor, said method comprising following computer-implemented steps:

• creating at least one reinforcement learning agent and at least one corresponding reinforcement learning environment using a first processor, and assigning a reinforcement learning agent ID to said reinforcement learning agent, and assigning a reinforcement learning environment ID to said reinforcement learning environment;
• creating an application-domain specific instruction set (ASI), and wherein said application-domain specific instruction set comprises vector based instructions for implementing reinforcement learning agents and reward functions;
• creating each of said instructions by incorporating at least one of the reinforcement learning agent ID vectors, the reinforcement learning environment ID vectors, and length of vector as an operand, and wherein the reinforcement learning agent ID vectors and the reinforcement learning environment ID vectors are pointers to a base address of an operations memory;
• selectively fetching at least one of said instructions, using a complex instruction fetch and decode (CISFD) unit, and decoding said instruction, and fetching agent vector from memory;
• embedding at least one of said reinforcement learning agent ID vector and reinforcement learning environment ID vector into operations associated with the decoded instruction;
• executing the instructions by agent ID vector indexed operation using a second processor, and applying the corresponding instruction onto a group of reinforcement learning agents and a group of reinforcement learning environments identified respectively by said reinforcement learning agent ID vector and reinforcement learning environment ID vector embedded in the instruction, and determining an action, a state-value function, a Q-value and a reward value, based on execution of the instruction corresponding to the operation;
• and
• storing operations defined by the instructions in an operations storage memory, wherein operations storage memory is a second memory.

A computer readable non-transitory storage medium having computer readable instructions stored thereupon, said computer readable instructions when executed by a computer processor, cause the computer processor to:

• creating at least one reinforcement learning agent and at least one corresponding reinforcement learning environment using a first processor, and assigning a reinforcement learning agent ID to said reinforcement learning agent, and assigning a reinforcement learning environment ID to said reinforcement learning environment;
• creating an application-domain specific instruction set (ASI), said application-domain specific instruction set comprising vector based instructions for implementing reinforcement learning agents and reward functions;
• creating each of said instructions by incorporating at least one of the reinforcement learning agent ID vectors, the reinforcement learning environment ID vectors, and length of vector as an operand, and wherein the reinforcement learning agent ID vectors and the reinforcement learning environment ID vectors are pointers to a base address of an operations memory;
• selectively fetching at least one of said instructions, using a complex instruction fetch and decode (CISFD) unit, and decoding said instruction, and fetching agent vector from memory;
• embedding at least one of said reinforcement learning agent ID vector and reinforcement learning environment ID vector into operations associated with the decoded instruction;
• executing the instructions fetched by agent ID vector indexed operation using a second processor, and applying the corresponding instruction onto a group of reinforcement learning agents and a group of reinforcement learning environments identified respectively by said reinforcement learning agent ID vector and reinforcement learning environment ID vector embedded in the instruction, and determining an action, a state-value function, a Q-value and a reward value, based on execution of the instruction corresponding to the operation;
• and
• storing operations defined by the instructions in an operations storage memory, wherein operations storage memory is a second memory.