Papers › Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning

Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning

15 Apr 2024arXiv:2404.09521archive 2025-07-28

Tidiane Camaret Ndir, André Biedenkapp, Noor Awad

In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and utilizing contextual cues, such as the gravity level of the environment, is critical for robust generalization, and we propose to integrate the learning of context representations directly with policy learning. Our algorithm demonstrates improved generalization on various simulated domains, outperforming prior context-learning techniques in zero-shot settings. By jointly learning policy and context, our method acquires behavior-specific context representations, enabling adaptation to unseen environments and marks progress towards reinforcement learning systems that generalize across diverse real-world tasks. Our code and experiments are available at https://github.com/tidiane-camaret/contextual_rl_zero_shot.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

tidiane-camaret/contextual_rl_zero_shot officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies (arXiv:2310.16686; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Reinforcement LearningReinforcement Learning (RL)Zero-shot Generalizationreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gravity

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections