Parallelized Synchronous Multi-agent Deep Reinforcement Learning with Experience Replay Memory.
Xudong GongBo DingJie XuHuaimin WangXing ZhouDawei FengPublished in: SOSE (2019)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- past experience
- reinforcement learning algorithms
- state space
- learning algorithm
- cooperative
- multi agent systems
- memory requirements
- temporal difference
- machine learning
- dynamic programming
- computing power
- intelligent agents
- markov decision processes
- learning agents
- memory space
- memory usage
- limited memory
- autonomous agents
- memory size
- multi agent environments
- single agent
- multi agent reinforcement learning
- heterogeneous agents
- reinforcement learning agents
- multiple agents
- optimal control
- user experience
- multiagent systems
- learning process
- action selection
- model free
- agent oriented
- computational power
- learning problems
- agent behavior
- reinforcement learning methods
- information processing
- learning environment
- multiagent reinforcement learning
- e learning