Part-Activated Deep Reinforcement Learning for Action Prediction.
Lei ChenJiwen LuZhanjie SongJie ZhouPublished in: ECCV (3) (2018)
Keyphrases
- reinforcement learning
- prediction accuracy
- partially observable domains
- action selection
- function approximation
- state action
- reward shaping
- prediction model
- action space
- prediction algorithm
- optimal control
- robotic control
- multi agent
- prediction error
- learning algorithm
- transition model
- state space
- machine learning
- optimal policy
- human actions
- markov decision processes
- regression model