SAPG：分割統合方策勾配法
SAPG: Split and Aggregate Policy Gradients
大規模並列環境を分割して重要度サンプリングで統合する新しいオンポリシー強化学習アルゴリズムSAPGを提案し、PPOを上回る性能を実現した。
著者: Jayesh Singla, Ananye Agarwal, Deepak Pathak
分類: cs.LG, cs.AI, cs.CV, cs.RO, cs.SY, eess.SY
原文アブストラクト
Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts of data for RL training has scaled exponentially. However, we show that current RL methods, e.g. PPO, fail to ingest the benefit of parallelized environments beyond a certain point and their performance saturates. To address this, we propose a new on-policy RL algorithm that can effectively leverage large-scale environments by splitting them into chunks and fusing them back together via importance sampling. Our algorithm, termed SAPG, shows significantly higher performance across a variety of challenging environments where vanilla PPO and other strong baselines fail to achieve high performance. Website at https://sapg-rl.github.io/
