Provable Reset-free Reinforcement Learning by No-Regret Reduction

Understand

Reinforcement learning (RL) so far has limited real-world applications.

• One key challenge is that typical RL algorithms heavily rely on a reset mechanism to sample proper initial states; these reset mechanisms, in practice, are expensive to implement due to the need for human intervention or heavily engineered environments.
• To make learning more practical, we propose a generic no-regret reduction to systematically design reset-free RL algorithms.
• Our reduction turns the reset-free RL problem into a two-player game.