Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms.
Filippo LazzatiMirco MuttiAlberto Maria MetelliPublished in: CoRR (2024)
Keyphrases
- solution concepts
- coalition formation
- game theoretic
- nash equilibrium
- game theory
- reinforcement learning
- von neumann
- coalitional games
- nash equilibria
- multi agent
- open questions
- cooperative game theory
- worst case
- markov decision processes
- optimal policy
- incomplete information
- state space
- dynamic programming
- multi agent systems
- cooperative games
- learning algorithm
- dynamic environments