Learning General World Models in a Handful of Reward-Free Deployments.
Yingchen XuJack Parker-HolderAldo PacchianoPhilip J. BallOleh RybkinStephen J. RobertsTim RocktäschelEdward GrefenstettePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning systems
- learning algorithm
- probabilistic model
- learning models
- accurate models
- neural network
- hidden variables
- special case
- active learning
- learning process
- supervised learning
- learning problems
- neural nets
- learned models
- knowledge acquisition
- model selection
- generative model
- experimental data
- learning tasks
- learning rules
- training data