ランダムウォークで目標を発見・到達:教師なしで多様なスキルを学ぶ
Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision
外部報酬やドメイン知識なしに、ランダムウォークで到達可能性ネットワークを訓練し、目標記憶を用いて目標条件付き方策を学習する手法を提案。連続制御ナビゲーションとロボットマニピュレーションに適用。
著者: Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Karteek Alahari
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications. We propose a novel method for training such a goal-conditioned agent without any external rewards or any domain knowledge. We use random walk to train a reachability network that predicts the similarity between two states. This reachability network is then used in building goal memory containing past observations that are diverse and well-balanced. Finally, we train a goal-conditioned policy network with goals sampled from the goal memory and reward it by the reachability network and the goal memory. All the components are kept updated throughout training as the agent discovers and learns new goals. We apply our method to a continuous control navigation and robotic manipulation tasks.
