学習が手の届かないときはリセット：自律視覚運動強化学習における汎化

原文アブストラクト

Episodic training, where an agent's environment is reset after every success or failure, is the de facto standard when training embodied reinforcement learning (RL) agents. The underlying assumption that the environment can be easily reset is limiting both practically, as resets generally require human effort in the real world and can be computationally expensive in simulation, and philosophically, as we'd expect intelligent agents to be able to continuously learn without intervention. Work in learning without any resets, i.e{.} Reset-Free RL (RF-RL), is promising but is plagued by the problem of irreversible transitions (e.g{.} an object breaking) which halt learning. Moreover, the limited state diversity and instrument setup encountered during RF-RL means that works studying RF-RL largely do not require their models to generalize to new environments. In this work, we instead look to minimize, rather than completely eliminate, resets while building visual agents that can meaningfully generalize. As studying generalization has previously not been a focus of benchmarks designed for RF-RL, we propose a new Stretch Pick-and-Place benchmark designed for evaluating generalizations across goals, cosmetic variations, and structural changes. Moreover, towards building performant reset-minimizing RL agents, we propose unsupervised metrics to detect irreversible transitions and a single-policy training mechanism to enable generalization. Our proposed approach significantly outperforms prior episodic, reset-free, and reset-minimizing approaches achieving higher success rates with fewer resets in Stretch-P\&P and another popular RF-RL benchmark. Finally, we find that our proposed approach can dramatically reduce the number of resets required for training other embodied tasks, in particular for RoboTHOR ObjectNav we obtain higher success rates than episodic approaches using 99.97\% fewer resets.