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...
主要な著者: | Igl, M, Zintgraf, L, Le, T, Wood, F, Whiteson, S |
---|---|
フォーマット: | Conference item |
出版事項: |
Journal of Machine Learning Research
2018
|
類似資料
-
Exploration in approximate hyper-state space for meta reinforcement learning
著者:: Zintgraf, L, 等
出版事項: (2021) -
Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs
著者:: Pineau, Joelle, 等
出版事項: (2017) -
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
著者:: Zintgraf, L, 等
出版事項: (2020) -
Multi-Agent Active Perception Based on Reinforcement Learning and POMDP
著者:: Tarik Selimovic, 等
出版事項: (2024-01-01) -
TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
著者:: Farquhar, G, 等
出版事項: (2018)