観測からの計画のためのモデル予測敵対的模倣学習
Model Predictive Adversarial Imitation Learning for Planning from Observation
逆強化学習のポリシーをモデル予測制御に置き換え、観測のみのデモから計画器をエンドツーエンドで学習する手法を提案し、サンプル効率や汎化性能の向上を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Tyler Han, Yanda Bao, Bhaumik Mehta, Gabriel Guo, Anubhav Vishwakarma, Emily Kang, Sanghun Jung, Rosario Scalise, Jason Zhou, Bryan Xu, Byron Boots
分類: cs.RO, cs.AI
原文アブストラクト
Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function via Inverse Reinforcement Learning (IRL) then deploying this reward via Model Predictive Control (MPC). Towards unifying these methods, we derive a replacement of the policy in IRL with a planning-based agent. With connections to Adversarial Imitation Learning, this formulation enables end-to-end interactive learning of planners from observation-only demonstrations. In addition to benefits in interpretability, complexity, and safety, we study and observe significant improvements on sample efficiency, out-of-distribution generalization, and robustness. The study includes evaluations in both simulated control benchmarks and real-world navigation experiments using few-to-single observation-only demonstrations.
