Multiagent Adversarial Inverse Reinforcement Learning.
Ermo WeiDrew WickeSean LukePublished in: AAMAS (2019)
Keyphrases
- inverse reinforcement learning
- multi agent
- bayesian nonparametric
- partially observable environments
- preference elicitation
- cooperative
- reward function
- multi agent systems
- multiple agents
- reinforcement learning
- multiagent systems
- single agent
- temporal difference
- markov decision process
- control policies
- machine learning
- theoretical framework
- artificial intelligence