Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic.
Wonseok JeonPaul BardeDerek NowrouzezahraiJoelle PineauPublished in: CoRR (2020)
Keyphrases
- inverse reinforcement learning
- multi agent
- bayesian nonparametric
- temporal difference
- partially observable environments
- preference elicitation
- reward function
- reinforcement learning
- reinforcement learning algorithms
- multi agent systems
- function approximation
- supervised learning
- hidden markov models
- state space
- monte carlo
- evaluation function
- special case
- cooperative