conftrace_

reward hacking

61 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reinforcement learning (21) reinforcement learning from human feedback (12) reward model (10) direct preference optimization (6) diffusion model (5) preference learning (5) reward modeling (5) language model (4) large language model (4) reward function (4)

Papers

Causal Confusion and Reward Misidentification in Preference-Based Reward Learning ICLR 2023 Language Model Alignment with Elastic Reset NeurIPS 2023 Reward Gaming in Conditional Text Generation ACL 2023 Defining and Characterizing Reward Gaming NeurIPS 2022 Direct Behavior Specification via Constrained Reinforcement Learning ICML 2022 Path-Specific Objectives for Safer Agent Incentives AAAI 2022 The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models ICLR 2022 Learning Human Objectives by Evaluating Hypothetical Behavior ICML 2020 Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences ICML 2020 Meta Learning for Image Captioning AAAI 2019 Inverse Reward Design NeurIPS 2017