バッチ・重み正規化によるオフポリシー強化学習のスケーリング
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
CrossQに重み正規化を組み込み、高い更新対データ比でも安定して学習できるようにし、連続制御タスクでのサンプル効率を改善した。
著者: Daniel Palenicek, Florian Vogt, Joe Watson, Jan Peters
分類: cs.LG, cs.AI
原文アブストラクト
Reinforcement learning has achieved significant milestones, but sample efficiency remains a bottleneck for real-world applications. Recently, CrossQ has demonstrated state-of-the-art sample efficiency with a low update-to-data (UTD) ratio of 1. In this work, we explore CrossQ's scaling behavior with higher UTD ratios. We identify challenges in the training dynamics, which are emphasized by higher UTD ratios. To address these, we integrate weight normalization into the CrossQ framework, a solution that stabilizes training, has been shown to prevent potential loss of plasticity and keeps the effective learning rate constant. Our proposed approach reliably scales with increasing UTD ratios, achieving competitive performance across 25 challenging continuous control tasks on the DeepMind Control Suite and Myosuite benchmarks, notably the complex dog and humanoid environments. This work eliminates the need for drastic interventions, such as network resets, and offers a simple yet robust pathway for improving sample efficiency and scalability in model-free reinforcement learning.
