URLB: Unsupervised Reinforcement Learning Benchmark.
Michael LaskinDenis YaratsHao LiuKimin LeeAlbert ZhanKevin LuCatherine CangLerrel PintoPieter AbbeelPublished in: NeurIPS Datasets and Benchmarks (2021)
Keyphrases
- reinforcement learning
- unsupervised learning
- supervised learning
- function approximation
- machine learning
- state space
- reinforcement learning algorithms
- semi supervised
- multi agent
- optimal policy
- temporal difference learning
- unsupervised manner
- unsupervised feature selection
- learning algorithm
- data driven
- genetic algorithm
- markov decision processes
- supervised classification
- robot control
- database
- multi agent reinforcement learning
- information bottleneck
- weakly supervised
- temporal difference
- mobile robot
- dynamic programming
- search engine
- real world
- data sets