Applying single-shot SNIP pruning with dataset-size-dependent sparsity reduces overfitting and improves episodic return of offline RL algorithms on 5k to 100k sample D4RL continuous control tasks.
Efficient reinforcement learning by discovering neural pathways
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
-
Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
Applying single-shot SNIP pruning with dataset-size-dependent sparsity reduces overfitting and improves episodic return of offline RL algorithms on 5k to 100k sample D4RL continuous control tasks.