世界モデルオンライン模倣学習のための結合分布的ランダムエキスパート蒸留
Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
世界モデルの潜在空間で専門家と行動方策の分布を同時推定するRNDベースの報酬モデルを提案し、オンライン模倣学習を安定化させた。
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: Shangzhe Li, Zhiao Huang, Hao Su
分類: cs.LG, cs.AI
原文アブストラクト
Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying on adversarial reward or value formulations in world model frameworks. In this work, we propose a novel approach to online imitation learning that addresses these limitations through a reward model based on random network distillation (RND) for density estimation. Our reward model is built on the joint estimation of expert and behavioral distributions within the latent space of the world model. We evaluate our method across diverse benchmarks, including DMControl, Meta-World, and ManiSkill2, showcasing its ability to deliver stable performance and achieve expert-level results in both locomotion and manipulation tasks. Our approach demonstrates improved stability over adversarial methods while maintaining expert-level performance.
