Transferring Domain Knowledge with an Adviser in Continuous Tasks
This addresses the inefficiency of trial-and-error learning in RL for continuous tasks, though it is incremental as it builds on existing DDPG methods.
The paper tackles the problem of reinforcement learning agents having to independently explore domain knowledge by adapting the DDPG algorithm to incorporate an adviser that integrates pre-learned policies or pre-defined relationships, resulting in expedited learning and improved policies on OpenAi Gym benchmark tasks.
Recent advances in Reinforcement Learning (RL) have surpassed human-level performance in many simulated environments. However, existing reinforcement learning techniques are incapable of explicitly incorporating already known domain-specific knowledge into the learning process. Therefore, the agents have to explore and learn the domain knowledge independently through a trial and error approach, which consumes both time and resources to make valid responses. Hence, we adapt the Deep Deterministic Policy Gradient (DDPG) algorithm to incorporate an adviser, which allows integrating domain knowledge in the form of pre-learned policies or pre-defined relationships to enhance the agent's learning process. Our experiments on OpenAi Gym benchmark tasks show that integrating domain knowledge through advisers expedites the learning and improves the policy towards better optima.