flâneur — a map of the web's best reading

Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data | HTML5

ar5iv.labs.arxiv.org · 24,500 words · saved by 1 readers

In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help improve the quality of the policy. Howev…

[2307.04354] Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data Ruiqi Zhang Department of Statistics University of California Berkeley rqzhang@berkeley.edu Andrea Zanette Department of EECS University of California Berkeley zanette@berkeley.edu Abstract In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help improve the quality of the policy. Howeve

Explore this link on the map →

related reading