局所一般化線形近似を用いた安全方策最適化
Safe Policy Optimization with Local Generalized Linear Function Approximations
センサーから得られる局所特徴と報酬・安全性の関係を一般化線形関数で学習しつつ、安全性と最適性の理論保証付きで方策を最適化するSPO-LFを提案した論文。
著者: Akifumi Wachi, Yunyue Wei, Yanan Sui
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply them to large-scale real problems. We propose a novel algorithm, SPO-LF, that optimizes an agent's policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety using generalized linear function approximations. We provide theoretical guarantees on its safety and optimality. We experimentally show that our algorithm is 1) more efficient in terms of sample complexity and computational cost and 2) more applicable to large-scale problems than previous safe RL methods with theoretical guarantees, and 3) comparably sample-efficient and safer compared with existing advanced deep RL methods with safety constraints.
