Reinforcement Learning from Imperfect Demonstrations.
Yang GaoHuazhe XuJi LinFisher YuSergey LevineTrevor DarrellPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- markov decision processes
- robotic control
- learning algorithm
- evolutionary learning
- model free
- optimal policy
- machine learning
- learning problems
- learning process
- partially observable
- policy search
- dynamic programming
- temporal difference
- real robot
- learning agent
- reinforcement learning methods
- artificial neural networks
- direct policy search