Continual Domain Randomization trains RL policies sequentially on randomization parameter subsets with continual learning to achieve robust sim-to-real transfer in robotic reaching and grasping.
Hypernetwork-PPO for Continual Reinforcement Learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Continual Domain Randomization
Continual Domain Randomization trains RL policies sequentially on randomization parameter subsets with continual learning to achieve robust sim-to-real transfer in robotic reaching and grasping.