Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data, which could lead to inaccurate predictions. As a result, RLHF may produce outputs that are misaligned with human values. To mitigate this issue, we contribute a reward ensemble method that allows the reward model to make more accurate predictions. As using an ensemble of large language model-based reward models can be computationally and resource-expensive, we explore efficient ensemble methods including linear-layer ensemble and LoRA-based ensemble. Empirically, we run Best-of-$n$ and Proximal Policy Optimization with our ensembled reward models, and verify that our ensemble methods help improve the alignment performance of RLHF outputs.
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…
RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai Jiao Tong University（上海交通大学）；Carnegie Mellon University（卡内基梅隆大学）；Jilin University（吉林大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. However, collecting a large preference comparison dataset is still expensive -- and the learned reward models are unreliable out-of-distribution. We seek to addre…
There is a rising interest in industrial online applications where data becomes available sequentially. Inspired by the recommendation of playlists to users where their preferences can be collected during the listening of the entire playlist, we study a novel bandit setting, namely Multi-Armed Bandit with Temporally-Partitioned Rewards (TP-MAB), in which the stochastic reward associated with the pull of an arm is partitioned over a finite number of consecutive rounds following the pull. This setting, unexplored so far to the best of our knowledge, is a natural extension of delayed-feedback ban…
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…
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…
We propose a generic reward shaping approach for improving the rate of convergence in reinforcement learning (RL), called Self Improvement Based REwards, or SIBRE. The approach is designed for use in conjunction with any existing RL algorithm, and consists of rewarding improvement over the agent's own past performance. We prove that SIBRE converges in expectation under the same conditions as the original RL algorithm. The reshaped rewards help discriminate between policies when the original rewards are weakly discriminated or sparse. Experiments on several well-known benchmark environments wit…
Fusing Reward and Dueling Feedback in Stochastic Bandits
University of Massachusetts（马萨诸塞大学）；City University of Hong Kong（香港城市大学）；Carnegie Mellon University（卡内基梅隆大学）；The Chinese University of Hong Kong（香港中文大学）；California Institute of Technology（加州理工学院）
Fluid human-agent communication is essential for the future of human-in-the-loop reinforcement learning. An agent must respond appropriately to feedback from its human trainer even before they have significant experience working together. Therefore, it is important that learning agents respond well to various feedback schemes human trainers are likely to provide. This work analyzes the COnvergent Actor-Critic by Humans (COACH) algorithm under three different types of feedback-policy feedback, reward feedback, and advantage feedback. For these three feedback types, we find that COACH can behave…
Samsung Research America（三星美国研究院）；University at Buffalo（布法罗大学）；Duke University（杜克大学）
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems. However, recommendations can easily violate preferences of users from their past natural-language feedback, since the recommender needs to explore new items for further improvement. To alleviate this issue, we propose a novel constraint-augmented reinforcement learning (RL) framework to efficiently incorporate user preferences over time. Specifically, we leverage a discriminator to detect recommendations violating user historical preference, whic…
Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
AI Research and Innovation Nexus for Africa (AIRINA Labs)（非洲AI研究与创新中心（AIRINA实验室））；Sefako Makgatho Health Sciences University (SMU)（塞法科·马加托健康科学大学）；African Center for Advanced Studies (ACAS)（非洲高级研究中心）；African Institute for Mathematical Sciences（非洲数学科学学院）
Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
National University of Defense Technology（国防科技大学）；State Key Laboratory of Complex & Critical Software Environment（复杂与关键软件环境国家重点实验室）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-…
A survey is performed of various Multi-Armed Bandit (MAB) strategies in order to examine their performance in circumstances exhibiting non-stationary stochastic reward functions in conjunction with delayed feedback. We run several MAB simulations to simulate an online eCommerce platform for grocery pick up, optimizing for product availability. In this work, we evaluate several popular MAB strategies, such as $ε$-greedy, UCB1, and Thompson Sampling. We compare the respective performances of each MAB strategy in the context of regret minimization. We run the analysis in the scenario where the re…
Automated lane change is one of the most challenging task to be solved of highly automated vehicles due to its safety-critical, uncertain and multi-agent nature. This paper presents the novel deployment of the state of art Q learning method, namely Rainbow DQN, that uses a new safety driven rewarding scheme to tackle the issues in an dynamic and uncertain simulation environment. We present various comparative results to show that our novel approach of having reward feedback from the safety layer dramatically increases both the agent's performance and sample efficiency. Furthermore, through the…
University of Washington（华盛顿大学）；Harvard University（哈佛大学）
We study a multi-armed bandit problem in a dynamic environment where arm rewards evolve in a correlated fashion according to a Markov chain. Different than much of the work on related problems, in our formulation a learning algorithm does not have access to either a priori information or observations of the state of the Markov chain and only observes smoothed reward feedback following time intervals we refer to as epochs. We demonstrate that existing methods such as UCB and $\varepsilon$-greedy can suffer linear regret in such an environment. Employing mixing-time bounds on Markov chains, we d…
The University of Queensland（昆士兰大学）；Intuitive Surgical（直觉外科公司）
Multiple-Intent Inverse Reinforcement Learning (MI-IRL) seeks to find a reward function ensemble to rationalize demonstrations of different but unlabelled intents. Within the popular expectation maximization (EM) framework for learning probabilistic MI-IRL models, we present a warm-start strategy based on up-front clustering of the demonstrations in feature space. Our theoretical analysis shows that this warm-start solution produces a near-optimal reward ensemble, provided the behavior modes satisfy mild separation conditions. We also propose a MI-IRL performance metric that generalizes the po…
