Heterogeneous-Agent Reinforcement Learning.
Yifan ZhongJakub Grudzien KubaSiyi HuJiaming JiYaodong YangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- intelligent agents
- multiagent systems
- multi agent systems
- single agent
- software agents
- multi agent environments
- autonomous agents
- autonomous learning
- learning capabilities
- agent model
- partially observable
- mobile agents
- markov decision process
- reward function
- markov decision processes
- state action
- state abstraction
- learning agents
- agent architecture
- multi agent reinforcement learning
- dynamic environments
- state space
- model free
- reinforcement learning algorithms
- function approximation
- optimal policy
- action space
- dynamic programming
- artificial agents
- learning algorithm
- multiagent learning
- reinforcement learning agents
- agent systems
- multi agent learning
- decision theoretic
- partially observable markov decision process
- mobile robot
- exploration strategy
- cooperative
- machine learning
- reward shaping
- agent receives