Zobrazeno 1 - 10
of 22 365
pro vyhledávání: '"imitation learning"'
Autor:
Veerapaneni, Rishi, Jakobsson, Arthur, Ren, Kevin, Kim, Samuel, Li, Jiaoyang, Likhachev, Maxim
Multi-Agent Path Finding (MAPF) is the problem of effectively finding efficient collision-free paths for a group of agents in a shared workspace. The MAPF community has largely focused on developing high-performance heuristic search methods. Recently
Externí odkaz:
http://arxiv.org/abs/2409.14491
Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically, and there i
Externí odkaz:
http://arxiv.org/abs/2411.01894
As a prominent category of imitation learning methods, adversarial imitation learning (AIL) has garnered significant practical success powered by neural network approximation. However, existing theoretical studies on AIL are primarily limited to simp
Externí odkaz:
http://arxiv.org/abs/2411.00610
Autor:
Kareer, Simar, Patel, Dhruv, Punamiya, Ryan, Mathur, Pranay, Cheng, Shuo, Wang, Chen, Hoffman, Judy, Xu, Danfei
The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data, specifically egocentric human videos paired wit
Externí odkaz:
http://arxiv.org/abs/2410.24221
Autor:
Jiang, Zhenyu, Xie, Yuqi, Lin, Kevin, Xu, Zhenjia, Wan, Weikang, Mandlekar, Ajay, Fan, Linxi, Zhu, Yuke
Imitation learning from human demonstrations is an effective means to teach robots manipulation skills. But data acquisition is a major bottleneck in applying this paradigm more broadly, due to the amount of cost and human effort involved. There has
Externí odkaz:
http://arxiv.org/abs/2410.24185
Autor:
Jiang, He, Wang, Yutong, Veerapaneni, Rishi, Duhan, Tanishq, Sartoretti, Guillaume, Li, Jiaoyang
Lifelong Multi-Agent Path Finding (LMAPF) is a variant of MAPF where agents are continually assigned new goals, necessitating frequent re-planning to accommodate these dynamic changes. Recently, this field has embraced learning-based methods, which r
Externí odkaz:
http://arxiv.org/abs/2410.21415
Autor:
Papagiannis, Georgios, Johns, Edward
Data collection in imitation learning often requires significant, laborious human supervision, such as numerous demonstrations, and/or frequent environment resets for methods that incorporate reinforcement learning. In this work, we propose an altern
Externí odkaz:
http://arxiv.org/abs/2410.19693
Imitation learning, which enables robots to learn behaviors from demonstrations by non-experts, has emerged as a promising solution for generating robot motions in such environments. The imitation learning based robot motion generation method, howeve
Externí odkaz:
http://arxiv.org/abs/2410.16981