One-shot random pruning at initialization lets deep RL networks keep improving at model sizes where dense networks collapse in performance.
Crossq: Batch normalization in deep reinforcement learning for greater sample efficiency and simplicity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
One-shot random pruning at initialization lets deep RL networks keep improving at model sizes where dense networks collapse in performance.