URLB: Unsupervised Reinforcement Learning Benchmark.
Michael LaskinDenis YaratsHao LiuKimin LeeAlbert ZhanKevin LuCatherine CangLerrel PintoPieter AbbeelPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- supervised learning
- unsupervised learning
- semi supervised
- temporal difference
- model free
- temporal difference learning
- multi agent
- optimal policy
- state space
- data driven
- supervised classification
- completely unsupervised
- database
- dynamic programming
- markov decision processes
- evaluation function
- learning process
- training data
- information retrieval
- learning capabilities
- robot control
- data mining
- stochastic approximation
- information bottleneck
- multi agent reinforcement learning
- real time