Reinforcement Learning
Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
Reinforcement Learning algorithms can be broadly classified into value-based methods and policy-based methods.
Mutual Information Regularized Offline Reinforcement Learning
We show that optimizing this lower bound is equivalent to maximizing the likelihood of a one-step improved policy on the offline dataset. Hence, we constrain the policy improvement direction to lie in the data manifold.
Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns.
Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns.
Inverse Preference Learning: Preference-based RL without a Reward Function
Reward functions are difficult to design and often hard to align with human intent.
