PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning.
Angelos FilosClare LyleYarin GalSergey LevineNatasha JaquesGregory FarquharPublished in: ICML (2021)
Keyphrases
- temporal difference learning
- reinforcement learning
- function approximation
- temporal difference
- learning algorithm
- learning process
- reinforcement learning algorithms
- game playing
- fixed point
- supervised learning
- learning tasks
- markov decision process
- evaluation function
- prior knowledge
- feature extraction
- markov decision processes
- function approximators
- machine learning
- action selection
- least squares
- multi agent
- rl algorithms