Deep Reinforcement Learning at the Edge of the Statistical Precipice.
Rishabh AgarwalMax SchwarzerPablo Samuel CastroAaron C. CourvilleMarc G. BellemarePublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- edge detection
- state space
- statistical analysis
- function approximation
- data driven
- markov decision processes
- information retrieval
- statistical models
- disjoint paths
- machine learning
- reinforcement learning algorithms
- edge information
- optimal control
- edge detector
- optimal policy
- dynamic programming
- learning process
- transfer learning
- shortest path
- supervised learning
- weighted graph
- confidence intervals
- statistical information
- hypothesis testing
- multiscale
- autonomous learning
- multi agent reinforcement learning
- bayesian networks