No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning.
Dianyu ZhongYiqin YangQianchuan ZhaoPublished in: CoRR (2023)
Keyphrases
- eliminate redundant
- reinforcement learning
- action selection
- action space
- partially observable domains
- state action
- function approximation
- state space
- prior knowledge
- model free
- reward shaping
- reinforcement learning algorithms
- markov decision processes
- transition model
- maximum a posteriori
- learning process
- action sequences
- neural network
- probability distribution
- action descriptions
- machine learning
- partially observable