Keyphrases
- partially observable
- reinforcement learning
- partially observable domains
- markov decision processes
- state space
- markov decision problems
- partial observability
- decision problems
- partial observations
- dynamical systems
- partially observable environments
- hidden state
- optimal policy
- infinite horizon
- learning algorithm
- reward function
- function approximation
- sufficient conditions
- reinforcement learning algorithms
- model free
- dynamic programming
- machine learning
- multi agent
- partially observable markov decision process
- action models
- partially observable markov decision processes
- belief state
- fully observable
- decision making
- temporal difference
- action space
- markov decision process
- supply chain
- computational complexity
- initially unknown
- transfer learning