FAST uses Dynamic Parallel Sampling Alignment via virtual continuation and Scaled Mask-Padding Optimization to remove straggler bottlenecks in parallel RL, delivering 1.78x wall-clock speedup while preserving unbiasedness.
Seed rl: Scalable and efficient deep-rl with accelerated central inference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
FAST uses Dynamic Parallel Sampling Alignment via virtual continuation and Scaled Mask-Padding Optimization to remove straggler bottlenecks in parallel RL, delivering 1.78x wall-clock speedup while preserving unbiasedness.