English
Related papers

Related papers: Physical Reasoning Using Dynamics-Aware Models

200 papers

Is dynamics prediction indispensable for physical reasoning? If so, what kind of roles do the dynamics prediction modules play during the physical reasoning process? Most studies focus on designing dynamics prediction networks and treating…

Machine Learning · Computer Science 2022-10-06 Shiqian Li , Kewen Wu , Chi Zhang , Yixin Zhu

Humans learn by observing, interacting with environments, and internalizing physics and causality. Here, we aim to ask whether an agent can similarly acquire human-like reasoning from interaction and keep improving with more experience. To…

Artificial Intelligence · Computer Science 2026-05-26 Mingyu Zhang , Lifeng Zhuo , Tianxi Tan , Guocan Xie , Xian Nie , Yan Li , Renjie Zhao , Zizhu He , Ziyu Wang , Jiting Cai , Yong-Lu Li

Physical reasoning is a crucial aspect in the development of general AI systems, given that human learning starts with interacting with the physical world before progressing to more complex concepts. Although researchers have studied and…

Artificial Intelligence · Computer Science 2023-12-19 Andrew Melnik , Robin Schiewer , Moritz Lange , Andrei Muresanu , Mozhgan Saeidi , Animesh Garg , Helge Ritter

Complex systems in science and engineering sometimes exhibit behavior that changes across different regimes. Traditional global models struggle to capture the full range of this complex behavior, limiting their ability to accurately…

Machine Learning · Computer Science 2023-07-24 Okezzi F. Ukorigho , Opeoluwa Owoyele

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…

Machine Learning · Computer Science 2025-07-02 Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart

Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a…

Machine Learning · Computer Science 2024-02-13 Yi Liu , Gaurav Datta , Ellen Novoseller , Daniel S. Brown

Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for robot task…

Artificial Intelligence · Computer Science 2020-09-02 Keting Lu , Shiqi Zhang , Peter Stone , Xiaoping Chen

The main challenge in developing effective reinforcement learning (RL) pipelines is often the design and tuning the reward functions. Well-designed shaping reward can lead to significantly faster learning. Naively formulated rewards,…

Robotics · Computer Science 2023-07-20 Se Hwan Jeon , Steve Heim , Charles Khazoom , Sangbae Kim

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Machine Learning · Computer Science 2025-06-19 Rui Yu , Shenghua Wan , Yucen Wang , Chen-Xiao Gao , Le Gan , Zongzhang Zhang , De-Chuan Zhan

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

Robotic systems that interact with the physical world must reason about kinematic and dynamic constraints imposed by their own embodiment, their environment, and the task at hand. We introduce KinDER, a benchmark for Kinematic and Dynamic…

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Machine Learning · Computer Science 2023-01-05 Daniel Shin , Anca D. Dragan , Daniel S. Brown

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Machine Learning · Computer Science 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

State-of-the-art model-based reinforcement learning methods train policies on imagined rollouts. These rollouts are trajectories generated by a learned dynamics model and are scored by a learned reward model, but without querying the true…

Machine Learning · Computer Science 2026-05-13 Nadav Timor , Ravid Shwartz-Ziv , Micah Goldblum , Yann LeCun , David Harel

Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…

Machine Learning · Computer Science 2026-04-24 Sukesh Subaharan

Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior…

Machine Learning · Computer Science 2020-11-20 Prasoon Goyal , Scott Niekum , Raymond J. Mooney

Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we…

Artificial Intelligence · Computer Science 2017-12-05 Yan Zhu , Shaoting Zhang , Dimitris Metaxas

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Artificial Intelligence · Computer Science 2025-08-12 Annie Wong , Thomas Bäck , Aske Plaat , Niki van Stein , Anna V. Kononova

Humans intuitively recognize objects' physical properties and predict their motion, even when the objects are engaged in complicated interactions. The abilities to perform physical reasoning and to adapt to new environments, while intrinsic…

Machine Learning · Computer Science 2020-06-30 Yunzhu Li , Toru Lin , Kexin Yi , Daniel M. Bear , Daniel L. K. Yamins , Jiajun Wu , Joshua B. Tenenbaum , Antonio Torralba

Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get…

Machine Learning · Computer Science 2020-01-13 Kai Jiang , XiaoLong Qin