Imitation Learning of Logical Program Policies for Multi-Agent Reinforcement Learning.
Manuel EberhardingerJohannes MaucherSetareh MaghsudiPublished in: KI (Workshops) (2022)
Keyphrases
- multi agent reinforcement learning
- imitation learning
- reinforcement learning
- optimal policy
- multi agent
- multi agent systems
- multi agent learning
- learning agents
- state space
- robotic systems
- maximum margin
- humanoid robot
- stochastic games
- control system
- markov chain
- learning problems
- hidden variables
- infinite horizon
- partially observable markov decision processes