Recent advancements in LLMs have revolutionized motion generation models in embodied applications. While LLM-type auto-regressive motion generation models benefit from training scalability, there remains a discrepancy between their token prediction objectives and human preferences. As a result, models pre-trained solely with token-prediction objectives often generate behaviors that deviate from what humans would prefer, making post-training preference alignment crucial for producing human-preferred motions. Unfortunately, post-training alignment requires extensive preference rankings of motions generated by the pre-trained model, which are costly to annotate, especially in multi-agent settings. Recently, there has been growing interest in leveraging pre-training demonstrations to scalably generate preference data for post-training alignment. However, these methods often adopt an adversarial assumption, treating all pre-trained model-generated samples as unpreferred examples. This adversarial approach overlooks the valuable signal provided by preference rankings among the model's own generations, ultimately reducing alignment effectiveness and potentially leading to misaligned behaviors. In this work, instead of treating all generated samples as equally bad, we leverage implicit preferences encoded in pre-training demonstrations to construct preference rankings among the pre-trained model's generations, offering more nuanced preference alignment guidance with zero human cost. We apply our approach to large-scale traffic simulation and demonstrate its effectiveness in improving the realism of pre-trained model's generated behaviors, making a lightweight 1M motion generation model comparable to SOTA large imitation-based models by relying solely on implicit feedback from pre-training demonstrations, without additional post-training human preference annotations or high computational costs.
Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm
Korea Military Academy (KMA)（韩国军事学院）；KAIST（韩国科学技术院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；University of California, Riverside（加州大学河滨分校）
Waseda University（早稻田大学）；Chongqing Technology and Business University（重庆工商大学）；Sun Yat-Sen University（中山大学）；Western Norway University of Applied Sciences（挪威西部应用科学大学）
The emergence of Artificial Intelligence of Things (AIoT) has provided novel insights for many social computing applications such as group recommender systems. As distance among people has been greatly shortened, it has been a more general demand to provide personalized services to groups instead of individuals. In order to capture group-level preference features from individuals, existing methods were mostly established via aggregation and face two aspects of challenges: secure data management workflow is absent, and implicit preference feedbacks is ignored. To tackle current difficulties, th…
Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which iteratively queries the user for her preferences between trajectories. In robotics however, IRL often struggles because it is difficult to get high-quality demonstrations; conversely, preference-based learning is very inefficient since it attempts to learn a continuous, high-dimensional function from binary feedback. We propose a new framework for reward lea…
Bosch Center for Artificial Intelligence（博世人工智能中心）
For prediction of interacting agents' trajectories, we propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning, has interpretable intermediate representations, and transfers to downstream decision making. It uses a net that reveals preferences from the agents' past joint trajectory, and a differentiable implicit layer that maps these preferences to local Nash equilibria, forming the modes of the predicted future trajectory. Additionally, it learns an equilibrium refinement concept. For tractability, we introduce a new class of continuous potential…
University of Bonn（波恩大学）；Fraunhofer FKIE（弗劳恩霍夫通信、信息处理与人机工程研究所）
For the most comfortable, human-aware robot navigation, subjective user preferences need to be taken into account. This paper presents a novel reinforcement learning framework to train a personalized navigation controller along with an intuitive virtual reality demonstration interface. The conducted user study provides evidence that our personalized approach significantly outperforms classical approaches with more comfortable human-robot experiences. We achieve these results using only a few demonstration trajectories from non-expert users, who predominantly appreciate the intuitive demonstrat…
Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations, (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where …
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results when using not only task-specific demonstrations but also task-agnostic albeit somewhat related demonstrations. In most cases, the available demonstrations are distilled into an implicit prior, commonly represented via a single deep net. Explicit priors in the form of a database that can be queried have also been shown to lead to encouraging results. To better benefit from availa…
As robots enter human environments, they will be expected to accomplish a tremendous range of tasks. It is not feasible for robot designers to pre-program these behaviors or know them in advance, so one way to address this is through end-user programming, such as via learning from demonstration (LfD). While significant work has been done on the mechanics of enabling robot learning from human teachers, one unexplored aspect is enabling mutual feedback between both the human teacher and robot during the learning process, i.e., implicit learning. In this paper, we explore one aspect of this mutua…
In the real world, RL agents should be rewarded for fulfilling human preferences. We show that RL agents implicitly learn the preferences of humans in their environment. Training a classifier to predict if a simulated human's preferences are fulfilled based on the activations of a RL agent's neural network gets .93 AUC. Training a classifier on the raw environment state gets only .8 AUC. Training the classifier off of the RL agent's activations also does much better than training off of activations from an autoencoder. The human preference classifier can be used as the reward function of an RL…
Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum
Seoul National University（首尔国立大学）；Artificial Intelligence Institute of Seoul National University (AIIS)（首尔国立大学人工智能研究所（AIIS））；Automation and Systems Research Institute (ASRI)（自动化与系统研究所（ASRI））
Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions from collected expert demonstrations. However, learning reward functions from demonstrations introduces many challenges: some methods require highly structured models, e.g. reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that on the other hand require tremendous amount of data. In additio…
University of California, Riverside（加州大学河滨分校）；Yale University（耶鲁大学）；Georgia Institute of Technology（佐治亚理工学院）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；University of Toronto（多伦多大学）
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）
Every home is different, and every person likes things done in their particular way. Therefore, home robots of the future need to both reason about the sequential nature of day-to-day tasks and generalize to user's preferences. To this end, we propose a Transformer Task Planner(TTP) that learns high-level actions from demonstrations by leveraging object attribute-based representations. TTP can be pre-trained on multiple preferences and shows generalization to unseen preferences using a single demonstration as a prompt in a simulated dishwasher loading task. Further, we demonstrate real-world d…
School of Computer and Information Engineering, Tianjin Normal University（天津师范大学计算机与信息工程学院）
In the implicit feedback recommendation, incorporating short-term preference into recommender systems has attracted increasing attention in recent years. However, unexpected behaviors in historical interactions like clicking some items by accident don't well reflect users' inherent preferences. Existing studies fail to model the effects of unexpected behaviors, thus achieve inferior recommendation performance. In this paper, we propose a Multi-Preferences Model (MPM) to eliminate the effects of unexpected behaviors. MPM first extracts the users' instant preferences from their recent historical…
Stanford Vision & Learning Lab（斯坦福视觉与学习实验室）；NVIDIA（英伟达）；University of Sydney（悉尼大学）；University of Washington（华盛顿大学）；University of Toronto（多伦多大学）
Learning from offline task demonstrations is a problem of great interest in robotics. For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task. However, leveraging a fixed batch of data can be problematic for larger datasets and longer-horizon tasks with greater variations. The data can exhibit substantial diversity and consist of suboptimal solution approaches. In this paper, we propose Implicit Reinforcement without Interaction at Scale (IRIS), a novel fram…
We investigate a learning decision support system for vehicle routing, where the routing engine learns implicit preferences that human planners have when manually creating route plans (or routings). The goal is to use these learned subjective preferences on top of the distance-based objective criterion in vehicle routing systems. This is an alternative to the practice of distinctively formulating a custom VRP for every company with its own routing requirements. Instead, we assume the presence of past vehicle routing solutions over similar sets of customers, and learn to make similar choices. T…
UC Berkeley（加州大学伯克利分校）；University of Amsterdam（阿姆斯特丹大学）；Stanford University（斯坦福大学）
Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what not to do. It is easy to forget these preferences, since these preferences are already satisfied in our environment. This motivates our key insight: when a robot is deployed in an environment that humans act in, the state of the environment is already optimized for what humans want. We can therefore use this implicit preference information from the state to…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Microsoft Research（微软研究院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors, while the policy agent learns to maximize this reward. In imitation learning, near-optimal expert data can be difficult to obtain, and even in the limit of infinite data cannot imply a total ordering over trajectories as preferences can. On the other hand, learning from preferences alone is challenging as a large number of preferences are required to infer a hig…
Microsoft Research（微软研究院）；MPI-SWS（马克斯·普朗克软件系统研究所）；ETH Zurich（苏黎世联邦理工学院）
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher's demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences that it additionally takes into consideration. These preferences can for example capture behavioral biases, mismatched worldviews, or physical constraints. We study two teaching approaches: learner-agnostic teaching, where the teacher provides demonstrations from an optimal policy …
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
Group recommender systems facilitate group decision making for a set of individuals (e.g., a group of friends, a team, a corporation, etc.). Many of these systems, however, either assume that (i) user preferences can be elicited (or inferred) and then aggregated into group preferences or (ii) group preferences are partially observed/elicited. We focus on making recommendations for a new group of users whose preferences are unknown, but we are given the decisions/choices of other groups. By formulating this problem as group recommendation from group implicit feedback, we focus on two of its pra…
Inferring the Unspoken: Aligning Embodied Agents with Implicit Preferences
Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；School of Computer Science & Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）；Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China（北京理工大学扬子江地区研究院）；National Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）
University of Tasmania（塔斯马尼亚大学）；MyState Bank（MyState银行）；Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）；University of Technology Sydney（悉尼科技大学）
The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. However, the judgement of preferences between trajectories is not dynamic and still requires human input over thousands of iterations. In this study, we proposed a weak human preference supervision framework, for which we developed a human preference scaling model that naturally reflects the human perception of the degree of weak choices between trajectories and estab…
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Key Laboratory of Big Data Management and Analysis Methods（大数据管理与分析方法北京市重点实验室）；Université de Montréal（蒙特利尔大学）
In this paper, we explore the problem of developing personalized chatbots. A personalized chatbot is designed as a digital chatting assistant for a user. The key characteristic of a personalized chatbot is that it should have a consistent personality with the corresponding user. It can talk the same way as the user when it is delegated to respond to others' messages. We present a retrieval-based personalized chatbot model, namely IMPChat, to learn an implicit user profile from the user's dialogue history. We argue that the implicit user profile is superior to the explicit user profile regardin…
This paper reveals a trap for artificial general intelligence (AGI) theorists who use economists' standard method of discounting. This trap is implicitly and falsely assuming that a rational AGI would have time-consistent preferences. An agent with time-inconsistent preferences knows that its future self will disagree with its current self concerning intertemporal decision making. Such an agent cannot automatically trust its future self to carry out plans that its current self considers optimal.
Renmin University of China（中国人民大学）；Peking University（北京大学）
The task of Knowledge Graph Completion (KGC) aims to automatically infer the missing fact information in Knowledge Graph (KG). In this paper, we take a new perspective that aims to leverage rich user-item interaction data (user interaction data for short) for improving the KGC task. Our work is inspired by the observation that many KG entities correspond to online items in application systems. However, the two kinds of data sources have very different intrinsic characteristics, and it is likely to hurt the original performance using simple fusion strategy. To address this challenge, we propose…
