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...
Những tác giả chính: | Igl, M, Zintgraf, L, Le, T, Wood, F, Whiteson, S |
---|---|
Định dạng: | Conference item |
Được phát hành: |
Journal of Machine Learning Research
2018
|
Những quyển sách tương tự
-
Exploration in approximate hyper-state space for meta reinforcement learning
Bằng: Zintgraf, L, et al.
Được phát hành: (2021) -
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs
Bằng: Pineau, Joelle, et al.
Được phát hành: (2017) -
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
Bằng: Zintgraf, L, et al.
Được phát hành: (2020) -
Multi-Agent Active Perception Based on Reinforcement Learning and POMDP
Bằng: Tarik Selimovic, et al.
Được phát hành: (2024-01-01) -
TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
Bằng: Farquhar, G, et al.
Được phát hành: (2018)