conftrace_

reward scaling

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reinforcement learning (2) module composability (1) domain-aware reward scaling (1) difficulty-aware reward scaling (1) unbiased sampling (1) group-based reinforcement learning (1) target normalization (1) overfitting (1) balanced reward distributions (1) history-based (1)

Papers

On the Hidden Objective Biases of Group-based Reinforcement Learning ACL 2026 ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning ICML 2025 DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data EMNLP 2025 Hyperspherical Normalization for Scalable Deep Reinforcement Learning ICML 2025 Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data ICML 2025 Symmetry-Aware GFlowNets ICML 2025 Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks NeurIPS 2023 Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning NeurIPS 2023 Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation NAACL 2021 Composable Modular Reinforcement Learning AAAI 2019 Learning values across many orders of magnitude NeurIPS 2016