Self-supervised learning has brought about a revolutionary paradigm shif...
Despite the recent advancements in offline reinforcement learning via
su...
We present a model-based offline reinforcement learning policy performan...
Offline reinforcement learning (RL) can be used to improve future perfor...
Offline policy optimization could have a large impact on many real-world...
Although Reinforcement Learning (RL) is effective for sequential
decisio...
Despite definite success in deep reinforcement learning problems,
actor-...
Policy gradient algorithms have proven to be successful in diverse decis...
A long-standing challenge in reinforcement learning is the design of fun...
Policy gradient algorithms in reinforcement learning rely on efficiently...