Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning.
Baicen XiaoBhaskar RamasubramanianRadha PoovendranPublished in: AAMAS (2022)
Keyphrases
- multi agent reinforcement learning
- learning agent
- multi agent
- reinforcement learning
- multi agent systems
- learning agents
- multi agent learning
- solving problems
- learning capabilities
- reward function
- learning tasks
- state space
- learning algorithm
- autonomous agents
- intelligent agents
- multiagent systems
- action selection
- stochastic games
- learning process
- cooperative
- reinforcement learning algorithms
- multiple agents
- game theory
- markov decision processes
- dynamic environments
- software agents
- single agent
- e learning
- state action
- decision making
- artificial intelligence
- machine learning
- knowledge based systems