Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks.
Haobo JiangJin XieJian YangPublished in: CoRR (2021)
Keyphrases
- continuous action
- continuous state and action spaces
- policy search
- continuous state
- reinforcement learning
- action space
- reinforcement learning algorithms
- state space
- action selection
- partially observable markov decision processes
- optimal policy
- transfer learning
- model free
- state action
- function approximation
- monte carlo
- dynamic environments
- dynamic programming
- cooperative