Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning.
Jun JinDaniel GravesCameron HaighJun LuoMartin JägersandPublished in: ICRA (2022)
Keyphrases
- reinforcement learning
- real world
- learning process
- learning algorithm
- knowledge acquisition
- real time
- prior knowledge
- learning problems
- supervised learning
- online learning
- learning systems
- active exploration
- function approximation
- learning tasks
- mobile devices
- wide range
- data sets
- learning experience
- active learning
- model free
- evolutionary learning
- state abstraction