[ICML 2023] Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

April 28, 2023

Abstract: While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode. Such an assumption hinders the autonomous learning of embodied a...

[ICLR 2023, Spotlight] Outcome-Directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

January 21, 2023

Abstract: Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a sequence of surrogate tasks, shows reasonable ...

[NeurIPS 2022] S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

November 1, 2022