強化学習のための最小で再利用可能な因果状態抽象化の構築
Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning
強化学習において、各タスクに必要な変数のみを保持する因果的な状態抽象化を学習する手法CBMを提案し、サンプル効率と汎化性能を向上させた。
著者: Zizhao Wang, Caroline Wang, Xuesu Xiao, Yuke Zhu, Peter Stone
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and improves implicit modeling to train a high-fidelity causal dynamics model that can be reused for all tasks in the same environment. Empirical validation on manipulation environments and Deepmind Control Suite reveals that CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones. Furthermore, the derived state abstractions allow a task learner to achieve near-oracle levels of sample efficiency and outperform baselines on all tasks.
