Markov decision processes with observation costs.
Christoph ReisingerJonathan TamPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- average cost
- optimal policy
- reinforcement learning
- finite state
- dynamic programming
- policy iteration
- state space
- transition matrices
- decision processes
- decision theoretic planning
- planning under uncertainty
- risk sensitive
- finite horizon
- reinforcement learning algorithms
- infinite horizon
- total cost
- partially observable
- reachability analysis
- average reward
- discounted reward
- markov decision process
- action space
- state abstraction
- data mining
- action sets
- expected cost
- real valued
- semi markov decision processes
- linear program
- real time dynamic programming