Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning.
Bilal KartalPablo Hernandez-LealMatthew E. TaylorPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- prediction accuracy
- prediction algorithm
- prediction error
- prediction model
- function approximation
- optimal policy
- neural network
- supervised learning
- robotic control
- real time
- reinforcement learning methods
- motion estimation
- evolutionary algorithm
- learning process
- multi agent
- bayesian networks
- website
- decision making
- real world