Keyphrases
- partially observable
- markov decision processes
- state space
- reinforcement learning
- markov decision problems
- decision problems
- dynamical systems
- partial observability
- infinite horizon
- decision diagrams
- action models
- reward function
- partial observations
- belief state
- partially observable environments
- optimal policy
- reinforcement learning algorithms
- dynamic programming
- finite state
- decision processes
- probabilistic planning
- dec pomdps
- machine learning
- average cost
- markov decision process
- policy iteration
- optimal control
- planning under uncertainty
- sufficient conditions
- multi agent
- learning algorithm