A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning.
Yonggan FuYongan ZhangChaojian LiZhongzhi YuYingyan LinPublished in: DAC (2021)
Keyphrases
- reinforcement learning
- multi agent
- search algorithm
- efficient search
- action selection
- multi agent systems
- search space
- agent systems
- search strategy
- multiagent systems
- autonomous agents
- autonomous learning
- agent model
- function approximation
- search methods
- intelligent agents
- state space
- dynamic programming
- multi agent environments
- action space
- markov decision processes
- intelligent search
- partially observable
- indexing structure
- software agents
- neural network
- mobile agents
- optimal solution
- decision making