A Workflow for Offline Model-Free Robotic Reinforcement Learning.
Aviral KumarAnikait SinghStephen TianChelsea FinnSergey LevinePublished in: CoRR (2021)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy iteration
- real robot
- robotic systems
- rl algorithms
- machine learning
- mobile robot
- optimal policy
- policy evaluation
- state space
- markov decision processes
- transfer learning
- dynamic programming
- reinforcement learning methods
- learning algorithm
- radial basis function
- semi supervised
- robot control
- temporal difference learning
- robotic arm
- multi agent