Hardness in Markov Decision Processes: Theory and Practice.
Michelangelo ConservaPaulo E. RauberPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- reinforcement learning
- state space
- transition matrices
- planning under uncertainty
- dynamic programming
- factored mdps
- reinforcement learning algorithms
- reachability analysis
- finite horizon
- action space
- model based reinforcement learning
- infinite horizon
- decision theoretic planning
- policy iteration
- decision processes
- partially observable
- markov decision process
- average reward
- np hard
- state abstraction
- average cost
- state and action spaces
- learning algorithm
- decision diagrams
- risk sensitive
- optimal solution
- action sets
- computational complexity
- semi markov decision processes
- heuristic search