https://openreview.net/forum?id=tIlCpCRyvM
Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization | OpenReview
Domain randomization (DR) is widely used in reinforcement learning (RL) to bridge the gap between simulation and reality by maximizing its average returns...
domain randomizationrelaxed staterevisitingviaadversarial
https://arxiv.org/abs/2109.13438
[2109.13438] Not Only Domain Randomization: Universal Policy with Embedding System Identification
Abstract page for arXiv paper 2109.13438: Not Only Domain Randomization: Universal Policy with Embedding System Identification
not onlydomain randomization
https://openreview.net/forum?id=T8vZHIRTrY
Understanding Domain Randomization for Sim-to-real Transfer | OpenReview
Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge...
domain randomizationunderstandingsimrealtransfer
https://openreview.net/forum?id=GXtmuiVrOM&referrer=%5Bthe%20profile%20of%20Gabriele%20Tiboni%5D(%2Fprofile%3Fid%3D~Gabriele_Tiboni1)
Domain Randomization via Entropy Maximization | OpenReview
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL)....
domain randomizationentropy maximizationviaopenreview