Planning and Learning in Partially Observable Systems via Filter Stability.
Noah GolowichAnkur MoitraDhruv RohatgiPublished in: STOC (2023)
Keyphrases
- partially observable
- reinforcement learning
- markov decision processes
- decision problems
- state space
- dynamical systems
- learning algorithm
- partial observations
- infinite horizon
- partially observable environments
- markov decision problems
- action models
- partial observability
- dynamic systems
- belief state
- machine learning
- complex systems
- partially observable domains