連続強化学習におけるモデルベース確率的価値勾配の再検討
On the model-based stochastic value gradient for continuous reinforcement learning
モデルフリーのソフト価値推定とモデルベースの確率的価値勾配を組み合わせることで、単純なモデルベースエージェントがモデルフリーの最先端手法をサンプル効率と最終報酬の両方で上回ることを示した論文。
著者: Brandon Amos, Samuel Stanton, Denis Yarats, Andrew Gordon Wilson
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing, their policies tend to lag behind those of model-free agents in terms of final reward, especially in non-trivial environments. In response, researchers have proposed model-based agents with increasingly complex components, from ensembles of probabilistic dynamics models, to heuristics for mitigating model error. In a reversal of this trend, we show that simple model-based agents can be derived from existing ideas that not only match, but outperform state-of-the-art model-free agents in terms of both sample-efficiency and final reward. We find that a model-free soft value estimate for policy evaluation and a model-based stochastic value gradient for policy improvement is an effective combination, achieving state-of-the-art results on a high-dimensional humanoid control task, which most model-based agents are unable to solve. Our findings suggest that model-based policy evaluation deserves closer attention.
関連論文
- 潜在想像によるパラメータ化行動空間の学習モデルベースRL
- チャンク単位のモデルベース方策最適化モデルベースRL
- モデルベース強化学習における動力学変化下でのリプレイ保持の特性評価モデルベースRL
- モデルベース強化学習のための償却低ランク適応モデルベースRL
- 変化点対応ワールドモデル:動力学シフトの検出と古いリプレイの忘却による回復モデルベースRL
- RENEW: 選好から世界モデルの学習とモデル悪用の修復を目指してモデルベースRL
