Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes.
Marc RigterBruno LacerdaNick HawesPublished in: AAAI (2021)
Keyphrases
- markov decision processes
- minimax regret
- planning under uncertainty
- decision theoretic planning
- optimal policy
- reward function
- state space
- partially observable
- transition matrices
- policy iteration
- reinforcement learning
- planning problems
- decision problems
- probabilistic planning
- incomplete information
- partially observable markov decision processes
- markov decision process
- heuristic search
- multi agent
- decision theoretic
- markov decision problems
- real time dynamic programming
- learning algorithm
- preference elicitation
- decision making