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