English
Related papers

Related papers: Self-Predictive Representations for Combinatorial …

200 papers

Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data…

Machine Learning · Computer Science 2021-03-17 Kianté Brantley , Soroush Mehri , Geoffrey J. Gordon

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

Machine Learning · Computer Science 2018-12-05 Ashvin Nair , Vitchyr Pong , Murtaza Dalal , Shikhar Bahl , Steven Lin , Sergey Levine

Hierarchical policies in offline goal-conditioned reinforcement learning (GCRL) addresses long-horizon tasks by decomposing control into high-level subgoal planning and low-level action execution. A critical design choice in such…

Machine Learning · Computer Science 2026-02-02 Jinu Hyeon , Woobin Park , Hongjoon Ahn , Taesup Moon

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable…

Machine Learning · Computer Science 2024-05-28 Seohong Park , Tobias Kreiman , Sergey Levine

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Aniket Didolkar , Andrii Zadaianchuk , Anirudh Goyal , Mike Mozer , Yoshua Bengio , Georg Martius , Maximilian Seitzer

Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused…

Machine Learning · Computer Science 2024-07-25 Hayato Watahiki , Ryo Iwase , Ryosuke Unno , Yoshimasa Tsuruoka

As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and…

Machine Learning · Computer Science 2023-05-18 Wenhao Ding , Haohong Lin , Bo Li , Ding Zhao

Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and dynamics model by bootstrapping from future latent…

Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinforcement learning (RL), in order to improve performance on…

Machine Learning · Computer Science 2025-12-19 Andrew Wagenmaker , Perry Dong , Raymond Tsao , Chelsea Finn , Sergey Levine

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn…

Artificial Intelligence · Computer Science 2025-10-28 Po-Chen Kuo , Han Hou , Will Dabney , Edgar Y. Walker

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Isabela Albuquerque , Nikhil Naik , Junnan Li , Nitish Keskar , Richard Socher

We propose a new policy representation based on score-based diffusion models (SDMs). We apply our new policy representation in the domain of Goal-Conditioned Imitation Learning (GCIL) to learn general-purpose goal-specified policies from…

Machine Learning · Computer Science 2023-06-02 Moritz Reuss , Maximilian Li , Xiaogang Jia , Rudolf Lioutikov

Contrastive Reinforcement Learning (CRL) provides a promising framework for extracting useful structured representations from unlabeled interactions. By pulling together state-action pairs and their corresponding future states, while…

Robotics · Computer Science 2025-07-23 Arsh Tangri , Nichols Crawford Taylor , Haojie Huang , Robert Platt

Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on…

Artificial Intelligence · Computer Science 2022-09-05 Minghuan Liu , Menghui Zhu , Weinan Zhang

Reinforcement learning faces significant challenges when applied to tasks characterized by sparse reward structures. Although imitation learning, within the domain of supervised learning, offers faster convergence, it relies heavily on…

Machine Learning · Computer Science 2025-09-04 Zeqiang Zhang , Fabian Wurzberger , Gerrit Schmid , Sebastian Gottwald , Daniel A. Braun

Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalization ability to achieve unseen goals is another fundamental…

Machine Learning · Computer Science 2023-06-05 Rui Yang , Yong Lin , Xiaoteng Ma , Hao Hu , Chongjie Zhang , Tong Zhang

We present Generative Predictive Control (GPC), an inference-time method for improving pretrained behavior-cloning policies without retraining. GPC augments a frozen diffusion policy at deployment with an action-conditioned world model…

Robotics · Computer Science 2026-03-13 Han Qi , Haocheng Yin , Aris Zhu , Yilun Du , Heng Yang

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Tianjun Zhang , Ruslan Salakhutdinov , Sergey Levine

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Shreyank N Gowda , Davide Moltisanti , Laura Sevilla-Lara

Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for…

Machine Learning · Computer Science 2026-01-05 John L. Zhou , Jonathan C. Kao