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...
Autors principals: | Igl, M, Zintgraf, L, Le, T, Wood, F, Whiteson, S |
---|---|
Format: | Conference item |
Publicat: |
Journal of Machine Learning Research
2018
|
Ítems similars
-
Exploration in approximate hyper-state space for meta reinforcement learning
per: Zintgraf, L, et al.
Publicat: (2021) -
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs
per: Pineau, Joelle, et al.
Publicat: (2017) -
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
per: Zintgraf, L, et al.
Publicat: (2020) -
Multi-Agent Active Perception Based on Reinforcement Learning and POMDP
per: Tarik Selimovic, et al.
Publicat: (2024-01-01) -
TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
per: Farquhar, G, et al.
Publicat: (2018)