Inverse Reinforcement Learning for Agents Behavior in a Crowd Simulator.
Nahum ÁlvarezItsuki NodaPublished in: MMAS (2018)
Keyphrases
- inverse reinforcement learning
- preference elicitation
- multi agent
- multi agent systems
- partially observable environments
- multiple agents
- bayesian nonparametric
- cooperative
- multiagent systems
- reward function
- utility function
- crowd behavior
- multi criteria
- resource allocation
- real robot
- decision making
- coalition formation
- single agent