Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zeng, Zilai"'
Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations. However, supporting novel goals or behaviors through reinforcement le
Externí odkaz:
http://arxiv.org/abs/2407.01903
Autor:
Yun, Tian, Zeng, Zilai, Handa, Kunal, Thapliyal, Ashish V., Pang, Bo, Pavlick, Ellie, Sun, Chen
Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads
Externí odkaz:
http://arxiv.org/abs/2311.02171
Recent work has demonstrated the effectiveness of formulating decision making as supervised learning on offline-collected trajectories. Powerful sequence models, such as GPT or BERT, are often employed to encode the trajectories. However, the benefit
Externí odkaz:
http://arxiv.org/abs/2307.03406
Recent work has demonstrated the effectiveness of formulating decision making as a supervised learning problem on offline-collected trajectories. However, the benefits of performing sequence modeling on trajectory data is not yet clear. In this work
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c87f1607e401654ae8ccfb14fa74cd0
http://arxiv.org/abs/2307.03406
http://arxiv.org/abs/2307.03406
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.