Efficient Deep Reinforcement Learning through Policy Transfer
AAMAS '19: International Conference on Autonomous Agents and Multiagent Systems Auckland New Zealand May, 2020, pp. 2053-2055, 2020.
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing TL approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. Howe...More
Full Text (Upload PDF)
PPT (Upload PPT)