Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression.
Fernando AceroZhibin LiPublished in: CoRR (2024)
Keyphrases
- gradient boosting
- symbolic regression
- reinforcement learning
- imitation learning
- genetic programming
- mobile robot
- optimal policy
- robotic systems
- gene expression programming
- loss function
- reward function
- evolutionary computation
- reinforcement learning methods
- vision system
- fitness function
- markov decision processes
- state space
- learning machines
- regression problems
- learning algorithm
- machine learning
- humanoid robot
- reinforcement learning algorithms
- evolutionary algorithm
- transfer learning
- model selection
- markov random field
- supervised learning
- semi supervised