English
Related papers

Related papers: Physical Reasoning Using Dynamics-Aware Models

200 papers

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

Machine Learning · Computer Science 2018-03-01 Sjoerd van Steenkiste , Michael Chang , Klaus Greff , Jürgen Schmidhuber

Mobile robot navigation in dynamic human environments requires policies that balance adaptability to diverse behaviors with compliance to safety constraints. We hypothesize that integrating data-driven rewards with rule-based objectives…

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Machine Learning · Computer Science 2021-06-03 Sindhu Padakandla

Physical learning is an emerging paradigm in science and engineering whereby (meta)materials acquire desired macroscopic behaviors by exposure to examples. So far, it has been applied to static properties such as elastic moduli and…

Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as epsilon-greedy. There are…

Machine Learning · Computer Science 2022-10-06 Per-Arne Andersen , Morten Goodwin , Ole-Christoffer Granmo

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

Machine Learning · Computer Science 2024-10-28 Qizhen Wu , Kexin Liu , Lei Chen

Reasoning about the behaviour of physical objects is a key capability of agents operating in physical worlds. Humans are very experienced in physical reasoning while it remains a major challenge for AI. To facilitate research addressing…

Artificial Intelligence · Computer Science 2021-08-31 Cheng Xue , Vimukthini Pinto , Chathura Gamage , Peng Zhang , Jochen Renz

Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments,…

Computation and Language · Computer Science 2020-01-10 Daniel M. Ziegler , Nisan Stiennon , Jeffrey Wu , Tom B. Brown , Alec Radford , Dario Amodei , Paul Christiano , Geoffrey Irving

A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a…

Machine Learning · Computer Science 2021-01-01 Stephen Tian , Suraj Nair , Frederik Ebert , Sudeep Dasari , Benjamin Eysenbach , Chelsea Finn , Sergey Levine

Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time. In this work, we demonstrate how to address this triple challenge by…

Machine Learning · Computer Science 2024-07-03 Zakariae El Asri , Olivier Sigaud , Nicolas Thome

Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based reasoning - a complex task requiring physics theorems and…

Artificial Intelligence · Computer Science 2025-05-27 Xinyu Zhang , Yuxuan Dong , Yanrui Wu , Jiaxing Huang , Chengyou Jia , Basura Fernando , Mike Zheng Shou , Lingling Zhang , Jun Liu

Designing dense rewards is crucial for reinforcement learning (RL), yet in robotics it often demands extensive manual effort and lacks scalability. One promising solution is to view task progress as a dense reward signal, as it quantifies…

Artificial Intelligence · Computer Science 2026-05-21 Yuyang Liu , Chuan Wen , Yihang Hu , Dinesh Jayaraman , Yang Gao

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Xuchen Li , Xuzhao Li , Jiahui Gao , Renjie Pi , Shiyu Hu , Wentao Zhang

Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on…

Machine Learning · Computer Science 2024-09-23 Narendra Patwardhan , Zequn Wang

Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 David Ding , Felix Hill , Adam Santoro , Malcolm Reynolds , Matt Botvinick

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large…

Artificial Intelligence · Computer Science 2023-01-18 Yuqian Jiang , Sudarshanan Bharadwaj , Bo Wu , Rishi Shah , Ufuk Topcu , Peter Stone

While using shaped rewards can be beneficial when solving sparse reward tasks, their successful application often requires careful engineering and is problem specific. For instance, in tasks where the agent must achieve some goal state,…

Artificial Intelligence · Computer Science 2019-11-05 Alexander Trott , Stephan Zheng , Caiming Xiong , Richard Socher

Reinforcement learning (RL) algorithms have proven transformative in a range of domains. To tackle real-world domains, these systems often use neural networks to learn policies directly from pixels or other high-dimensional sensory input.…

Machine Learning · Computer Science 2025-10-02 Nishil Patel , Sebastian Lee , Stefano Sarao Mannelli , Sebastian Goldt , Andrew Saxe

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

Systems and Control · Electrical Eng. & Systems 2023-04-25 Wuxia Chen , Taposh Banerjee , Jemin George , Carl Busart

In this paper, we present an exploration of LLMs' abilities to problem solve with physical reasoning in situated environments. We construct a simple simulated environment and demonstrate examples of where, in a zero-shot setting, both text…

Computation and Language · Computer Science 2024-02-27 Sadaf Ghaffari , Nikhil Krishnaswamy