Residual Reinforcement Learning from Demonstrations.
Minttu AlakuijalaGabriel Dulac-ArnoldJulien MairalJean PonceCordelia SchmidPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- optimal control
- machine learning
- action space
- temporal difference learning
- learning process
- expert systems
- hidden markov models
- multi agent
- supervised learning
- markov decision processes
- learning problems
- policy search
- model free
- temporal difference
- robotic control
- continuous state
- stochastic approximation
- real world
- direct policy search
- control problems
- partially observable
- multiscale
- search engine
- learning algorithm
- data mining