Robust Q-learning algorithm for Markov decision processes under Wasserstein uncertainty.
Ariel NeufeldJulian SesterPublished in: Autom. (2024)
Keyphrases
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- reinforcement learning
- state space
- finite state
- optimal policy
- transition matrices
- policy iteration
- average cost
- reachability analysis
- factored mdps
- decision theoretic planning
- finite horizon
- planning under uncertainty
- partially observable
- dynamic programming
- infinite horizon
- risk sensitive
- reward function
- markov chain
- robust optimization
- action space
- decision processes
- average reward
- supervised learning
- machine learning
- model based reinforcement learning
- policy evaluation
- probabilistic planning
- finite number