Prediction and Control in Continual Reinforcement Learning.
Nishanth AnandDoina PrecupPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal control
- control problems
- prediction accuracy
- process control
- action selection
- function approximation
- prediction model
- robot control
- model free
- control strategy
- markov decision processes
- dynamic programming
- control system
- multi agent
- control policies
- robotic control
- inverted pendulum
- prediction algorithm
- real time
- temporal difference
- adaptive control
- prediction error
- learning algorithm
- machine learning