Stabilizing Multi-Agent Deep Reinforcement Learning by Implicitly Estimating Other Agents' Behaviors.
Yue JinShuangqing WeiJian YuanXudong ZhangChao WangPublished in: ICASSP (2020)
Keyphrases
- multi agent
- reinforcement learning
- multi agent systems
- agent behavior
- agent interactions
- single agent
- multiple agents
- multi agent environments
- intelligent agents
- learning agents
- multiagent systems
- cooperative
- multi agent reinforcement learning
- autonomous agents
- heterogeneous agents
- agent cooperation
- reinforcement learning agents
- state space
- multi agent coordination
- multi agent simulation
- multiagent learning
- agent based simulations
- multi agent planning
- crowd simulation
- agent communication
- function approximation
- software agents
- multiagent reinforcement learning
- reactive agents
- learning algorithm
- minority game
- real robot
- cooperative agents
- team formation
- multiagent environments
- multi agent learning
- agent oriented
- coalition formation
- markov decision processes
- state abstraction
- cooperative behavior
- evolutionary learning
- agent systems
- reinforcement learning algorithms
- temporal difference
- action selection
- agent architecture
- robocup rescue
- partially observable stochastic games