Skip to content
conftrace_

proxy reward

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reward hacking (3) reinforcement learning (3) human feedback (2) episodic return decomposition (1) video comprehension (1) return decomposition (1) worst-case reward (1) unhackable proxy (1) corrective action (1) value-based deep reinforcement learning (1)

Papers

Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation ICML 2025 Reinforcement Learning from Imperfect Corrective Actions and Proxy Rewards ICLR 2025 Unhackable Temporal Reward for Scalable Video MLLMs ICLR 2025 When Can Proxies Improve the Sample Complexity of Preference Learning? ICML 2025 Episodic Return Decomposition by Difference of Implicitly Assigned Sub-trajectory Reward AAAI 2024 Goodhart's Law in Reinforcement Learning ICLR 2024 Rethinking the Role of Proxy Rewards in Language Model Alignment EMNLP 2024 Defining and Characterizing Reward Gaming NeurIPS 2022 Learning Long-Term Reward Redistribution via Randomized Return Decomposition ICLR 2022 The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models ICLR 2022