LGAIROMLOct 27, 2020

Conservative Safety Critics for Exploration

arXiv:2010.14497v2160 citations
Originality Incremental advance
AI Analysis

This addresses the problem of ensuring safety during active data collection in RL for applications like navigation and manipulation, though it is incremental as it builds on existing safe RL methods.

The paper tackles safe exploration in reinforcement learning by learning a conservative safety critic to upper bound catastrophic failures during training, achieving competitive task performance with significantly lower failure rates than prior methods.

Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still enabling trial and error learning. In this paper, we target the problem of safe exploration in RL by learning a conservative safety estimate of environment states through a critic, and provably upper bound the likelihood of catastrophic failures at every training iteration. We theoretically characterize the tradeoff between safety and policy improvement, show that the safety constraints are likely to be satisfied with high probability during training, derive provable convergence guarantees for our approach, which is no worse asymptotically than standard RL, and demonstrate the efficacy of the proposed approach on a suite of challenging navigation, manipulation, and locomotion tasks. Empirically, we show that the proposed approach can achieve competitive task performance while incurring significantly lower catastrophic failure rates during training than prior methods. Videos are at this url https://sites.google.com/view/conservative-safety-critics/home

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes