Complementary Learning System Based Intrinsic Reward in Reinforcement Learning.
Zijian GaoKele XuHongda JiaTianjiao WanBo DingDawei FengXinjun MaoHuaimin WangPublished in: ICASSP (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning agent
- partially observable environments
- learning systems
- state space
- learning problems
- eligibility traces
- learning agents
- optimal control
- multi agent
- reinforcement learning algorithms
- action selection
- function approximation
- learning tasks
- training data
- supervised learning
- unsupervised learning
- online learning
- e learning
- reinforcement learning methods
- actor critic
- policy search
- multi agent systems
- active exploration
- neural network