Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences.
Raphael KösterKevin R. McKeeRichard EverettLaura WeidingerWilliam S. IsaacEdward HughesEdgar A. Duéñez-GuzmánThore GraepelMatthew BotvinickJoel Z. LeiboPublished in: CoRR (2020)
Keyphrases
- model free
- multi agent reinforcement learning
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- stochastic games
- temporal difference
- multi agent
- learning agents
- policy iteration
- markov decision processes
- multi agent learning
- learning agent
- state space
- temporal difference learning
- average reward
- rl algorithms
- action selection
- machine learning
- learning problems
- transfer learning
- multi agent systems
- training data