Exploration in environments which differ across episodes has received increasing attention
in recent years. Current methods use some combination of global novelty bonuses …

Abstract We present AIRS: Automatic Intrinsic Reward Sha** that intelligently and
adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement …

Traditional information theory provides a valuable foundation for Reinforcement Learning,
particularly through representation learning and entropy maximization for agent exploration …

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set
diverse goals to learn a set of skills. Despite the excellent works proposed in various fields …

Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks.
However, extrinsic rewards frequently fall short in complex environments due to the …

Optimizing techniques for discovering molecular structures with desired properties is crucial
in artificial intelligence (AI)-based drug discovery. Combining deep generative models with …

Sparse-reward reinforcement learning environments pose a particular challenge because
the agent receives infrequent rewards, making it difficult to learn an optimal policy. In this …

Exploration is one of the central topic in reinforcement learning (RL). Many existing
approaches take a single agent perspective when tackling this problem. In this work, we …