Minigo: A Case Study in Reproducing Reinforcement Learning Research.
Brian LeeAndrew JacksonTom MadamsSeth TroisiDerek JonesPublished in: RML@ICLR (2019)
Keyphrases
- reinforcement learning
- state space
- case study
- function approximation
- test bed
- reinforcement learning algorithms
- optimal control
- model free
- multi agent
- markov decision processes
- dynamic programming
- real time
- decision making
- learning algorithm
- optimal policy
- machine learning
- data sets
- continuous state
- multi agent reinforcement learning
- transfer learning
- monte carlo
- sufficient conditions
- least squares
- learning process
- computer vision
- genetic algorithm