Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks.
Haobo JiangJin XieJian YangPublished in: CoRR (2022)
Keyphrases
- continuous action
- policy search
- reinforcement learning
- continuous state
- continuous state and action spaces
- action space
- reinforcement learning algorithms
- state space
- partially observable markov decision processes
- cooperative
- state action
- learning algorithm
- decision making
- reward function
- evaluation function
- state dependent
- markov decision processes
- control system
- multi agent
- neural network