VariBAD: variational bayes-adaptive deep RL via meta-learning
Trading off exploration and exploitation in an unknown environment is key to maximising expected online return during learning. A Bayes-optimal policy, which does so optimally, conditions its actions not only on the environment state but also on the agent's uncertainty about the environment. Co...
主要作者: | Whiteson, S |
---|---|
格式: | Journal article |
語言: | English |
出版: |
Journal of Machine Learning Research
2021
|
相似書籍
-
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
由: Zintgraf, L, et al.
出版: (2020) -
Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function
由: Marko Ruman, et al.
出版: (2024-01-01) -
PharmRL: pharmacophore elucidation with deep geometric reinforcement learning
由: Rishal Aggarwal, et al.
出版: (2024-12-01) -
Fast Context Adaptation via Meta-Learning
由: Zintgraf, L, et al.
出版: (2019) -
Experience Replay Optimisation via ATSC and TSC for Performance Stability in Deep RL
由: Richard Sakyi Osei, et al.
出版: (2023-02-01)