深層強化学習における自己教師あり探索のための変分動的モデル
Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
環境の状態遷移を条件付き変分推論でモデル化し、その負の対数尤度の上界を内在的報酬として自己教師あり探索を行う手法を提案。画像ベースのシミュレーションと実ロボット操作で既存手法を上回る性能を示した。
著者: Chenjia Bai, Peng Liu, Kaiyu Liu, Lingxiao Wang, Yingnan Zhao, Lei Han
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show promising results in simple environments but often get stuck in environments with multimodal and stochastic dynamics. In this work, we propose a variational dynamic model based on the conditional variational inference to model the multimodality and stochasticity. We consider the environmental state-action transition as a conditional generative process by generating the next-state prediction under the condition of the current state, action, and latent variable, which provides a better understanding of the dynamics and leads a better performance in exploration. We derive an upper bound of the negative log-likelihood of the environmental transition and use such an upper bound as the intrinsic reward for exploration, which allows the agent to learn skills by self-supervised exploration without observing extrinsic rewards. We evaluate the proposed method on several image-based simulation tasks and a real robotic manipulating task. Our method outperforms several state-of-the-art environment model-based exploration approaches.
