Learning Optimal Advantage from Preferences and Mistaking it for Reward
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Research（谷歌研究院）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；UC Berkeley（加州大学伯克利分校）；Sony AI（索尼人工智能）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur Orn Adalgeirsson, Serena Booth, Anca Dragan, Peter Stone, Scott Niekum
备注：
8 pages (16 pages with references and appendix), 11 figures
We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return. Recent work casts doubt on the validity of this assumption, proposing an alternative preference model based upon regret. We investigate the consequences of assuming preferences are based upon partial return when they actually arise from regret. We argue that the learned function is an approximation of the optimal advantage function, $\hat{A^*_r}$, not a reward function. We find that if a specific pitfall is addressed, this incorrect assumption is not particularly harmful, resulting in a highly shaped reward function. Nonetheless, this incorrect usage of $\hat{A^*_r}$ is less desirable than the appropriate and simpler approach of greedy maximization of $\hat{A^*_r}$. From the perspective of the regret preference model, we also provide a clearer interpretation of fine tuning contemporary large language models with RLHF. This paper overall provides insight regarding why learning under the partial return preference model tends to work so well in practice, despite it conforming poorly to how humans give preferences.
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating human feedback, i.e. teacher's preferences between two clips of behaviors. However, poor feedback-efficiency still remains a problem in current preference-based RL algorithms, as tailored human feedback is very expensive. To handle this issue, previous methods have mainly focused on improving query selection and policy initialization. At the same time, rece…
University of Bristol（布里斯托大学）；CortAIx, Thales（泰雷兹公司 CortAIx）
The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward function is inferred from sparse human feedback. However, prior PbRL methods lack interpretability of the learned reward structure, which hampers the ability to assess robustness and alignment. We propose an online, active preference learning algorithm that constructs reward functions with the intrinsically interpretable, compositional structure of a tree. Usi…
Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt to approximate the human's underlying reward function capturing their preferences. In this work, we investigate the issue of a high degree of variability in the initialized reward models which are sensitive to random seeds of the experiment. This further compounds the issue of degenerate reward functions PbRL methods already suffer from. We propose a data-driven reward initialization method that does not add any addi…
KAIST（韩国科学技术院）；University of Michigan（密歇根大学）；LG AI Research（LG人工智能研究院）；UC Berkeley（加州大学伯克利分校）
Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent behaviors. However, preference-based learning often requires a large amount of human feedback, making it difficult to apply this approach to various applications. This data-efficiency problem, on the other hand, has been typically addressed by using unlabeled samples or data augmentation techniques in the context of supervised learning. Motivated by the recent su…
We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback. Our method improves prior work by generalising human preferences, reducing the burden on the user and increasing the robustness of the reward model. We demonstrate this with a number of experiments.
PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
TCS Research, \ of CSE, IIT Madras India；Department of Computing Science, \ of Alberta Canada；Qatar Computing Research Institute, \ Bin Khalifa University Qatar；Department of Data Science \& AI, Wadhwani School of Data Science \& AI, IIT Madras India；TCS Research, \ of CSE, IIT Madras；Department of Computing Science, \ of Alberta；Qatar Computing Research Institute, \ Bin Khalifa University；Department of Data Science \& AI, Wadhwani School of Data Science \& AI, IIT Madras
Specifying rewards for reinforcement learned (RL) agents is challenging. Preference-based RL (PbRL) mitigates these challenges by inferring a reward from feedback over sets of trajectories. However, the effectiveness of PbRL is limited by the amount of feedback needed to reliably recover the structure of the target reward. We present the PRIor Over Rewards (PRIOR) framework, which incorporates priors about the structure of the reward function and the preference feedback into the reward learning process. Imposing these priors as soft constraints on the reward learning objective reduces the amou…
Preference-based reinforcement learning (RL) algorithms help avoid the pitfalls of hand-crafted reward functions by distilling them from human preference feedback, but they remain impractical due to the burdensome number of labels required from the human, even for relatively simple tasks. In this work, we demonstrate that encoding environment dynamics in the reward function (REED) dramatically reduces the number of preference labels required in state-of-the-art preference-based RL frameworks. We hypothesize that REED-based methods better partition the state-action space and facilitate generali…
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Institute of Engineering Research, Korea University（韩国大学工程研究所）；Kim Jaechul Graduate School of AI, KAIST（韩国科学技术院金在哲人工智能研究生院）；Industrial Management Engineering, Korea University（韩国大学产业管理工程学院）
University of Cambridge（剑桥大学）；University of California, Los Angeles（加州大学洛杉矶分校）；The Alan Turing Institute（艾伦·图灵研究所）
Modeling the preferences of agents over a set of alternatives is a principal concern in many areas. The dominant approach has been to find a single reward/utility function with the property that alternatives yielding higher rewards are preferred over alternatives yielding lower rewards. However, in many settings, preferences are based on multiple, often competing, objectives; a single reward function is not adequate to represent such preferences. This paper proposes a method for inferring multi-objective reward-based representations of an agent's observed preferences. We model the agent's prio…
Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried trajectory pairs by a human in the loop indicating their preferences about the agent's behavior to learn a reward model. In this work, we present a state augmentation technique that allows the agent's reward model to be robust and follow an invariance consistency that significantly improved performance, i.e. the reward recovery and subsequent return computed u…
Learning in Context, Guided by Choice: A Reward-Free Paradigm for Reinforcement Learning with Transformers
Department of Electrical and Computer Engineering, Duke University, Durham, US（电子工程系，杜克大学，达勒姆，美国）；Department of Computer Science, Duke University, Durham, US（计算机科学系，杜克大学，达勒姆，美国）；Department of Biostatistics and Bioinformatics, Duke University, Durham, US（生物统计学与生物信息学系，杜克大学，达勒姆，美国）；Department of Statistics and Data Science, Yale University, New Haven, US（统计学与数据科学系，耶鲁大学，纽 Haven，美国）
GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO
College of Computing and Data Science,Nanyang Technological University (NTU), Singapore（南洋理工大学计算与数据科学学院）；Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly(LILY),NTU,Singapore（南洋理工大学与UBC联合卓越老年活跃生活研究中心（LILY））
IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
HUJING Digital Media \& Entertainment Group (XingYun Lab), Beijing, China；Department of Automation, Tsinghua University, Beijing, China；Fudan University, Shanghai, China；Beihang University, Beijing, China；Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
Models of human preference for learning reward functions
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Bosch（博世）；Google Research（谷歌研究院）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Sony AI（索尼人工智能研究院）
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games…
Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学计算机科学与工程保罗·G·艾伦学校）；Max Planck Institute for Intelligent Systems, Tübingen, Germany（德国图宾根马克斯·普朗克智能系统研究所）；Jinesis Lab, University of Toronto & Vector Institute（多伦多大学Jinesis实验室及向量研究所）
