Deep Reinforcement Learning at the Edge of the Statistical Precipice.
Rishabh AgarwalMax SchwarzerPablo Samuel CastroAaron C. CourvilleMarc G. BellemarePublished in: NeurIPS (2021)
Keyphrases
- reinforcement learning
- function approximation
- statistical analysis
- neural network
- temporal difference
- markov decision processes
- data driven
- temporal difference learning
- statistical approaches
- multiple scales
- information theoretic
- dynamic programming
- information retrieval
- machine learning
- optimal policy
- transfer learning
- markov chain
- learning problems
- edge detector
- image segmentation
- edge information
- statistical information
- information systems
- real time