深層混合エキスパートによる文脈依存方策転移
Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts
複数のシミュレーションで学習した方策を実世界に転移するため、状態に応じてソースタスクのダイナミクスを混合エキスパートで推定し、モデルフリー学習者へ文脈的に知識転移する手法を提案した。
著者: Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
分類: cs.LG, cs.NE, cs.RO, cs.SY, eess.SY
原文アブストラクト
In reinforcement learning, agents that consider the context, or current state, when selecting source policies for transfer have been shown to outperform context-free approaches. However, none of the existing approaches transfer knowledge contextually from model-based learners to a model-free learner. This could be useful, for instance, when source policies are intentionally learned on diverse simulations with plentiful data but transferred to a real-world setting with limited data. In this paper, we assume knowledge of estimated source task dynamics and policies, and common sub-goals but different dynamics. We introduce a novel deep mixture-of-experts formulation for learning state-dependent beliefs over source task dynamics that match the target dynamics using state trajectories collected from the target task. The mixture model is easy to interpret, demonstrates robustness to estimation errors in dynamics, and is compatible with most learning algorithms. We then show how this model can be incorporated into standard policy reuse frameworks, and demonstrate its effectiveness on benchmarks from OpenAI-Gym.
