Isaac Gym achieves 2-3 orders of magnitude faster robot policy training by keeping physics simulation and PyTorch-based RL entirely on GPU with direct buffer sharing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2021 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
Isaac Gym achieves 2-3 orders of magnitude faster robot policy training by keeping physics simulation and PyTorch-based RL entirely on GPU with direct buffer sharing.