DAMPER: Return-Prioritized Gradient Control for Smooth Policies
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/komin0407/DAMPER
Sources
- Adapting Auxiliary Losses Using Gradient Similarity
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
- Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods
- Gymnasium: A Standard Interface for Reinforcement Learning Environments
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks