paper-with-me

홈 › Papers

Horizon Generalization in Reinforcement Learning

2025-01-06 · Vivek Myers, Catherine Ji, Benjamin Eysenbach

We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon: after training to reach nearby goals (which are easy to learn), these policies should succeed in reaching distant goals (which are quite challenging to learn). In the same way that invariance is closely linked with generalization is other areas of machine learning (e.g., normalization layers make a network invariant to scale, and therefore generalize to inputs of varying scales), we show that this notion of horizon generalization is closely linked with invariance to planning: a policy navigating towards a goal will select the same actions as if it were navigating to a waypoint en route to that goal. Thus, such a policy trained to reach nearby goals should succeed at reaching arbitrarily-distant goals. Our theoretical analysis proves that both horizon generalization and planning invariance are possible, under some assumptions. We present new experimental results and recall findings from prior work in support of our theoretical results. Taken together, our results open the door to studying how techniques for invariance and generalization developed in other areas of machine learning might be adapted to achieve this alluring property.

📄 PDF Abstract BibTeX arXiv:2501.02709

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

On the Importance of Multistability for Horizon Generalization in Reinforcement Learning

2026-05-12 · Asad Bakija, Florent De Geeter, Julien Brandoit, Pierre Sacré 외 arxiv

In reinforcement learning (RL), agents acting in partially observable Markov decision processes (POMDPs) must rely on memory, typically encoded in a recurrent neural network (RNN), to integrate information from past obse…

Reinforcement Learning

Offline Reinforcement Learning with Universal Horizon Models

2026-05-15 · Hojun Chung, Junseo Lee, Songhwai Oh arxiv

Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from compounding errors due to repeated model in…

Reinforcement LearningOffline RL

Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

2021-11-04 · ICLR 2022 4 · Dhruv Shah, Peng Xu, Yao Lu, Ted Xiao 외

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lo…

Hierarchical Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning

2026-05-25 · Hyungkyu Kang, Byeongchan Kim, Min-hwan Oh arxiv

Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon…

Reinforcement Learning

Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion

2026-02-02 · Dan Haramati, Carl Qi, Tal Daniel, Amy Zhang 외 arxiv

We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multip…

Reinforcement Learning