スケジュールされた内発的ドライブ：階層的な内発的動機付け探索
Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
内発的・外発的方策を別々に学習し、探索とタスク遂行をスケジュールで切り替える階層的強化学習手法を提案。軌道全体の統計を用いる新たな内発的報酬SFCにより、視覚入力環境での探索効率を大幅に改善した。
著者: Jingwei Zhang, Niklas Wetzel, Nicolai Dorka, Joschka Boedecker, Wolfram Burgard
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration. Commonly these signals are added as bonus rewards, which results in a mixture policy that neither conducts exploration nor task fulfillment resolutely. In this paper, we instead learn separate intrinsic and extrinsic task policies and schedule between these different drives to accelerate exploration and stabilize learning. Moreover, we introduce a new type of intrinsic reward denoted as successor feature control (SFC), which is general and not task-specific. It takes into account statistics over complete trajectories and thus differs from previous methods that only use local information to evaluate intrinsic motivation. We evaluate our proposed scheduled intrinsic drive (SID) agent using three different environments with pure visual inputs: VizDoom, DeepMind Lab and DeepMind Control Suite. The results show a substantially improved exploration efficiency with SFC and the hierarchical usage of the intrinsic drives. A video of our experimental results can be found at https://youtu.be/b0MbY3lUlEI.
