Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning.
Baicen XiaoBhaskar RamasubramanianRadha PoovendranPublished in: CoRR (2022)
Keyphrases
- multi agent reinforcement learning
- learning agent
- multi agent
- reinforcement learning
- multi agent systems
- learning agents
- multi agent learning
- state space
- learning algorithm
- solving problems
- learning capabilities
- multiagent systems
- stochastic games
- learning tasks
- single agent
- reinforcement learning algorithms
- reward function
- autonomous agents
- intelligent agents
- game theory
- dynamic environments
- learning process
- decision making
- multiple agents
- state action
- machine learning
- action selection
- temporal difference
- long run