English
Related papers

Related papers: AbideGym: Turning Static RL Worlds into Adaptive C…

200 papers

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Machine Learning · Computer Science 2025-09-04 Sherry Yang , Joy He-Yueya , Percy Liang

A key challenge for reinforcement learning (RL) consists of learning in environments with sparse extrinsic rewards. In contrast to current RL methods, humans are able to learn new skills with little or no reward by using various forms of…

As agentic systems increasingly rely on reinforcement learning from verifiable rewards, standardized ``gym'' infrastructure has become essential for rapid iteration, reproducibility, and fair comparison. Vision agents lack such…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Fanqing Meng , Lingxiao Du , Jiawei Gu , Jiaqi Liao , Linjie Li , Zijian Wu , Xiangyan Liu , Ziqi Zhao , Mengkang Hu , Zichen Liu , Jiaheng Zhang , Michael Qizhe Shieh

Controlling a non-statically bipedal robot is challenging due to the complex dynamics and multi-criterion optimization involved. Recent works have demonstrated the effectiveness of deep reinforcement learning (DRL) for simulation and…

Robotics · Computer Science 2021-12-23 Changxin Huang , Guangrun Wang , Zhibo Zhou , Ronghui Zhang , Liang Lin

Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade agent performance. A promising approach involves learning…

Machine Learning · Computer Science 2025-04-04 JB Lanier , Kyungmin Kim , Armin Karamzade , Yifei Liu , Ankita Sinha , Kat He , Davide Corsi , Roy Fox

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view…

Machine Learning · Computer Science 2018-12-04 Ozsel Kilinc , Giovanni Montana

Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence. In this paper, we cast the problem of continuous adaptation into the…

Machine Learning · Computer Science 2018-02-26 Maruan Al-Shedivat , Trapit Bansal , Yuri Burda , Ilya Sutskever , Igor Mordatch , Pieter Abbeel

Intelligent systems have the ability to improve their behaviour over time taking observations, experiences or explicit feedback into account. Traditional approaches separate the learning problem and make isolated use of techniques from…

Machine Learning · Computer Science 2022-01-12 Simon Reichhuber , Sven Tomforde

Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially…

Computation and Language · Computer Science 2026-05-19 Fei Bai , Huatong Song , Shuang Sun , Daixuan Cheng , Yike Yang , Chuan Hao , Renyuan Li , Feng Chang , Yuan Wei , Ran Tao , Bryan Dai , Jian Yang , Wayne Xin Zhao , Ji-Rong Wen

Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics,…

Robotics · Computer Science 2021-10-22 Maximilian Ulmer , Elie Aljalbout , Sascha Schwarz , Sami Haddadin

In neuroscience, one of the key behavioral tests for determining whether a subject of study exhibits model-based behavior is to study its adaptiveness to local changes in the environment. In reinforcement learning, however, recent studies…

Machine Learning · Computer Science 2024-05-28 Safa Alver , Ali Rahimi-Kalahroudi , Doina Precup

World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training,…

Artificial Intelligence · Computer Science 2025-06-03 Shenyuan Gao , Siyuan Zhou , Yilun Du , Jun Zhang , Chuang Gan

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and…

Machine Learning · Computer Science 2023-01-02 Seyed Roozbeh Razavi Rohani , Saeed Hedayatian , Mahdieh Soleymani Baghshah

Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($\rho$) and update…

Machine Learning · Computer Science 2026-04-30 Quang-Hung Bui , Anh Son Ta

Recommender Systems are becoming ubiquitous in many settings and take many forms, from product recommendation in e-commerce stores, to query suggestions in search engines, to friend recommendation in social networks. Current research…

Information Retrieval · Computer Science 2018-09-17 David Rohde , Stephen Bonner , Travis Dunlop , Flavian Vasile , Alexandros Karatzoglou

Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to…

Multiagent Systems · Computer Science 2026-04-22 Jenny Ma , Riya Sahni , Karthik Sreedhar , Lydia B. Chilton

Multi-agent reinforcement learning experiments and open-source training environments are typically limited in scale, supporting tens or sometimes up to hundreds of interacting agents. In this paper we demonstrate the use of Vogue, a high…

Multiagent Systems · Computer Science 2022-07-11 Jordan Langham-Lopez , Sebastian M. Schmon , Patrick Cannon

Autonomous driving faces challenges in navigating complex real-world traffic, requiring safe handling of both common and critical scenarios. Reinforcement learning (RL), a prominent method in end-to-end driving, enables agents to learn…

Robotics · Computer Science 2026-03-09 Ahmed Abouelazm , Johannes Ratz , Philip Schörner , J. Marius Zöllner

A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistical significance, and risks degrading user experience. We present SimGym, a framework for…

Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation of memory. Existing memory benchmarks rely on static, off-policy…

Computation and Language · Computer Science 2026-03-03 Cheng Jiayang , Dongyu Ru , Lin Qiu , Yiyang Li , Xuezhi Cao , Yangqiu Song , Xunliang Cai