Distributional Reachability for Markov Decision Processes: Theory and Applications.
Yulong GaoAlessandro AbateLihua XieKarl Henrik JohanssonPublished in: IEEE Trans. Autom. Control. (2024)
Keyphrases
- markov decision processes
- state space
- reinforcement learning
- finite state
- optimal policy
- transition matrices
- dynamic programming
- policy iteration
- reachability analysis
- planning under uncertainty
- reinforcement learning algorithms
- average cost
- finite horizon
- decision theoretic planning
- model based reinforcement learning
- markov decision process
- infinite horizon
- decision processes
- action space
- risk sensitive
- reward function
- action sets
- factored mdps
- heuristic search
- average reward
- partially observable
- state and action spaces
- discounted reward
- state abstraction
- data mining
- function approximation
- planning problems
- sufficient conditions
- markov chain
- search space
- optimal solution
- learning algorithm