DG-PG augments policy gradients with descent signals from analytical models to reduce estimator variance from O(N) to O(1), preserve game equilibria, and achieve agent-independent sample complexity while converging on 1500-agent tasks where baselines fail.
Policy gradient meth- ods for reinforcement learning with function approximation.Advances in neural information processing systems, 12, 1999
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
Soft-DPG uses Gaussian smoothing on the Bellman equation to derive a well-defined policy gradient without relying on critic action derivatives, yielding competitive performance on dense-reward tasks and gains on discretized-reward variants.
KRPO uses a Kalman filter to estimate latent prompt-level reward baselines from per-group rewards in GRPO, yielding better reward curves and accuracy on math reasoning benchmarks.
citing papers explorer
-
Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
DG-PG augments policy gradients with descent signals from analytical models to reduce estimator variance from O(N) to O(1), preserve game equilibria, and achieve agent-independent sample complexity while converging on 1500-agent tasks where baselines fail.
-
On the Sample Complexity of Differentially Private Policy Optimization
Differential privacy in policy optimization adds sample complexity costs that often appear as lower-order terms rather than dominating the bounds.
-
Soft Deterministic Policy Gradient with Gaussian Smoothing
Soft-DPG uses Gaussian smoothing on the Bellman equation to derive a well-defined policy gradient without relying on critic action derivatives, yielding competitive performance on dense-reward tasks and gains on discretized-reward variants.
-
Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning
KRPO uses a Kalman filter to estimate latent prompt-level reward baselines from per-group rewards in GRPO, yielding better reward curves and accuracy on math reasoning benchmarks.