Markov Decision Processes with Noisy State Observation.
Amirhossein AfsharradSanjay LallPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- state space
- action space
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- markov decision process
- partially observable
- dynamic programming
- policy iteration
- reachability analysis
- decision processes
- real time dynamic programming
- state abstraction
- finite horizon
- planning under uncertainty
- decision theoretic planning
- factored mdps
- machine learning
- risk sensitive
- discounted reward
- state variables
- dynamical systems
- state and action spaces
- total reward
- data mining
- partially observable markov decision processes
- model based reinforcement learning
- markov chain
- heuristic search
- average reward
- average cost