Deep variational reinforcement learning for POMDPs
Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given only a stream of incomplete and noisy observations. In this...
Main Authors: | Igl, M, Zintgraf, L, Le, T, Wood, F, Whiteson, S |
---|---|
格式: | Conference item |
出版: |
Journal of Machine Learning Research
2018
|
相似書籍
-
Exploration in approximate hyper-state space for meta reinforcement learning
由: Zintgraf, L, et al.
出版: (2021) -
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs
由: Pineau, Joelle, et al.
出版: (2017) -
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
由: Zintgraf, L, et al.
出版: (2020) -
Multi-Agent Active Perception Based on Reinforcement Learning and POMDP
由: Tarik Selimovic, et al.
出版: (2024-01-01) -
TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
由: Farquhar, G, et al.
出版: (2018)