予測情報で強化学習の学習を加速する
Predictive Information Accelerates Learning in RL
過去と未来の相互情報である予測情報を圧縮表現として補助タスクで学習し、SACエージェントのサンプル効率をDM Controlで大幅に改善した論文。
著者: Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee, John Canny, Sergio Guadarrama
分類: cs.LG, cs.AI, cs.IT, cs.RO, math.IT, stat.ML
原文アブストラクト
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL, since the ability to model what will happen next is necessary for success on many tasks. To test our hypothesis, we train Soft Actor-Critic (SAC) agents from pixels with an auxiliary task that learns a compressed representation of the predictive information of the RL environment dynamics using a contrastive version of the Conditional Entropy Bottleneck (CEB) objective. We refer to these as Predictive Information SAC (PI-SAC) agents. We show that PI-SAC agents can substantially improve sample efficiency over challenging baselines on tasks from the DM Control suite of continuous control environments. We evaluate PI-SAC agents by comparing against uncompressed PI-SAC agents, other compressed and uncompressed agents, and SAC agents directly trained from pixels. Our implementation is given on GitHub.
