EasySO: Exploration-enhanced Reinforcement Learning for Logic Synthesis Sequence Optimization and a Comprehensive RL Environment.
Jianyong YuanPeiyu WangJunjie YeMingxuan YuanJianye HaoJunchi YanPublished in: ICCAD (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- exploration strategy
- logic synthesis
- learning agent
- action selection
- machine learning
- reinforcement learning algorithms
- function approximation
- model free
- markov decision processes
- temporal difference
- unknown environments
- exploration exploitation
- real time
- multi agent
- autonomous learning
- state space
- optimization algorithm
- agent learns
- reward signal
- action space
- heuristic search
- multi valued
- optimal policy
- learning classifier systems
- active exploration
- partially observable domains
- robocup soccer
- exploration exploitation tradeoff