English
Related papers

Related papers: Better World Models Can Lead to Better Post-Traini…

200 papers

A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate through the resulting computational graph to learn a policy. However, this method often becomes…

Machine Learning · Computer Science 2024-02-13 Michel Ma , Tianwei Ni , Clement Gehring , Pierluca D'Oro , Pierre-Luc Bacon

This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve…

We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method…

Machine Learning · Computer Science 2026-01-23 Patrick Altmeyer , Aleksander Buszydlik , Arie van Deursen , Cynthia C. S. Liem

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the…

Machine Learning · Computer Science 2024-10-30 Qi Wang , Junming Yang , Yunbo Wang , Xin Jin , Wenjun Zeng , Xiaokang Yang

The ability to predict upcoming events has been hypothesized to comprise a key aspect of natural and machine cognition. This is supported by trends in deep reinforcement learning (RL), where self-supervised auxiliary objectives such as…

Artificial Intelligence · Computer Science 2024-10-31 Ching Fang , Kimberly L Stachenfeld

Neural architectures inspired by our own human cognitive system, such as the recently introduced world models, have been shown to outperform traditional deep reinforcement learning (RL) methods in a variety of different domains. Instead of…

Neural and Evolutionary Computing · Computer Science 2019-06-24 Sebastian Risi , Kenneth O. Stanley

Enabling VLA models to predict environmental dynamics, known as world modeling, has been recognized as essential for improving robotic reasoning and generalization. However, current approaches face two main issues: 1. The training objective…

Robotics · Computer Science 2026-02-20 Han Zhao , Jingbo Wang , Wenxuan Song , Shuai Chen , Yang Liu , Yan Wang , Haoang Li , Donglin Wang

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a…

Machine Learning · Statistics 2024-06-06 Michael E. Sander , Raja Giryes , Taiji Suzuki , Mathieu Blondel , Gabriel Peyré

World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-based environments, world models are typically evaluated and…

The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs of such dynamics models are sparsely connected, with each of…

We introduce the framework of performative reinforcement learning where the policy chosen by the learner affects the underlying reward and transition dynamics of the environment. Following the recent literature on performative…

Machine Learning · Computer Science 2023-06-08 Debmalya Mandal , Stelios Triantafyllou , Goran Radanovic

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Machine Learning · Computer Science 2019-05-16 Kai Olav Ellefsen , Jim Torresen

Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number…

Robotics · Computer Science 2026-03-03 Yanjiang Guo , Lucy Xiaoyang Shi , Jianyu Chen , Chelsea Finn

Training self-driving systems to be robust to the long-tail of driving scenarios is a critical problem. Model-based approaches leverage simulation to emulate a wide range of scenarios without putting users at risk in the real world. One…

Robotics · Computer Science 2022-04-18 Vlad Sobal , Alfredo Canziani , Nicolas Carion , Kyunghyun Cho , Yann LeCun

Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and…

Machine Learning · Computer Science 2026-05-27 Xiaoyuan Cheng , Wenxuan Yuan , Zhancun Mu , Yuanzhao Zhang , Yiming Yang , Hai Wang , Zhuo Sun , Che Liu

The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Gabriele Merlin , Vedant Nanda , Ruchit Rawal , Mariya Toneva

AI systems deployed in the real world must contend with distractions and out-of-distribution (OOD) noise that can destabilize their policies and lead to unsafe behavior. While robust training can reduce sensitivity to some forms of noise,…

Machine Learning · Computer Science 2025-12-02 Geigh Zollicoffer , Tanush Chopra , Mingkuan Yan , Xiaoxu Ma , Kenneth Eaton , Mark Riedl

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Minbyul Jeong , Jaewoo Kang

Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement…

Artificial Intelligence · Computer Science 2023-01-18 Jonathan Balloch , Zhiyu Lin , Robert Wright , Xiangyu Peng , Mustafa Hussain , Aarun Srinivas , Julia Kim , Mark O. Riedl

Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable approach shifting the expensive combinatorial search to a…

Machine Learning · Computer Science 2025-09-25 Henrik Voigt , Paul Kahlmeyer , Kai Lawonn , Michael Habeck , Joachim Giesen