Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems.
Masatoshi UeharaAyush SekhariJason D. LeeNathan KallusWen SunPublished in: CoRR (2022)
Keyphrases
- partially observable
- dynamical systems
- reinforcement learning
- state space
- partial observability
- partially observable domains
- partially observable environments
- dynamic systems
- hidden state
- markov decision processes
- markov decision problems
- action models
- partial observations
- decision problems
- infinite horizon
- partially observable markov decision processes
- belief state
- machine learning
- partially observable markov decision process
- reward function
- graphical models
- multi agent
- decision making