One-shot sim-to-real transfer policy for robotic assembly via reinforcement learning with visual demonstration.
Ruihong XiaoChenguang YangYiming JiangHui ZhangPublished in: Robotica (2024)
Keyphrases
- reinforcement learning
- optimal policy
- transfer learning
- visual information
- real robot
- robotic tasks
- policy search
- action selection
- robot programming
- reinforcement learning problems
- markov decision process
- mobile robot
- function approximation
- real world
- partially observable environments
- reinforcement learning algorithms
- state space
- neural network
- high level
- function approximators
- approximate dynamic programming
- state action
- partially observable domains
- multi agent
- supervised learning
- continuous state spaces
- rl algorithms
- infinite horizon
- dynamic pricing
- visual features
- markov decision processes
- knowledge transfer
- reward function
- temporal difference
- autonomous robots