Transferring Domain Knowledge with an Adviser in Continuous Tasks [article]

Rukshan Wijesinghe, Kasun Vithanage, Dumindu Tissera, Alex Xavier, Subha Fernando, Jayathu Samarawickrama
2021 arXiv   pre-print
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
more » ... 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.
arXiv:2102.08029v1 fatcat:44k3ziahsra2rg6mxuzlatjuzy