Exploiting Symmetry and Heuristic Demonstrations in Off-policy Reinforcement Learning for Robotic Manipulation.
Amir M. Soufi EnayatiZengjie ZhangKashish GuptaHomayoun NajjaranPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- manipulation tasks
- dynamic programming
- real robot
- function approximation
- perception action
- real time
- combinatorial optimization
- symmetry detection
- model free
- optimal solution
- search algorithm
- learning algorithm
- reinforcement learning algorithms
- state space
- mobile robot
- tabu search
- robotic systems
- constraint satisfaction
- markov decision processes
- temporal difference
- robot control
- temporal difference learning
- policy search
- genetic algorithm
- machine learning
- action selection
- robot navigation
- multi agent systems
- vision system