Robust Q-learning Algorithm for Markov Decision Processes under Wasserstein Uncertainty.
Ariel NeufeldJulian SesterPublished in: CoRR (2022)
Keyphrases
- markov decision processes
- learning algorithm
- reinforcement learning
- reinforcement learning algorithms
- state space
- optimal policy
- finite state
- transition matrices
- dynamic programming
- policy iteration
- action space
- infinite horizon
- average cost
- planning under uncertainty
- model based reinforcement learning
- decision theoretic planning
- finite horizon
- average reward
- reachability analysis
- state and action spaces
- markov decision process
- robust optimization
- partially observable
- decision processes
- policy evaluation
- risk sensitive
- factored mdps
- function approximation
- multi agent
- action sets
- model free
- real valued