Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization
Lu Wen,Songan Zhang,H. Eric Tseng,Baljeet Singh,Dimitar Filev,Huei Peng,Lu Wen,Songan Zhang,H. Eric Tseng,Baljeet Singh,Dimitar Filev,Huei Peng
Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. Probabilistic embeddings for actor-critic $\boldsymbol{RL}$ (PEARL) is a leading approach for multi-MDP adaptation problems. A major drawback of many existing Meta-RL methods, including PEARL, is that they do not ex...