Research Area:  Machine Learning
In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected randomly for replay. However, the achieved goals in the replay buffer are often biased towards the behavior policies. From a Bayesian perspective, when there is no prior knowledge about the target goal distribution, the agent should learn uniformly from diverse achieved goals. Therefore, we first propose a novel multi-goal RL objective based on weighted entropy. This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals. Secondly, we developed a maximum entropy-based prioritization framework to optimize the proposed objective. For evaluation of this framework, we combine it with Deep Deterministic Policy Gradient, both with or without Hindsight Experience Replay. On a set of multi-goal robotic tasks of OpenAI Gym, we compare our method with other baselines and show promising improvements in both performance and sample-efficiency.
Keywords:  
Author(s) Name:  Rui Zhao, Xudong Sun, Volker Tresp
Journal name:  
Conferrence name:  Proceedings of the 36th International Conference on Machine Learning
Publisher name:  PMLR
DOI:  https://doi.org/10.48550/arXiv.1905.08786
Volume Information:  
Paper Link:   http://proceedings.mlr.press/v97/zhao19d.html