Jan Benad | Searcharxiv

arXiv2026

Dynamics-Aligned Shared Hypernetworks for Contextual RL under Discontinuous Shifts

Zero-shot generalization in contextual reinforcement learning remains a core challenge, particularly when the context is latent and must be inferred from data. A canonical failure mode arises when latent context discontinuously changes how actions affect the environment, requiring incompatible control responses across contexts. We propose DMA*-SH, a framework where a single hypernetwork, trained solely via dynamics prediction, generates a small set of adapter weights shared across the dynamics model, policy, and action-value function. This shared modulation imparts an inductive bias matched to discontinuous context-to-dynamics shifts, while input/output normalization and random input masking stabilize context inference, promoting directionally concentrated representations. We provide theoretical support via expressivity separation results for hypernetwork modulation, and a variance decomposition with policy-gradient variance bounds that formalize how within-mode compression improves learning under non-overlapping contexts. For evaluation, we introduce the Actuator Inversion Benchmark (AIB), a suite of environments designed to isolate challenging context-to-dynamics interactions, including actuator inversion, actuator permutations, and weakly non-overlapping continuous dynamics. On AIB's held-out tasks, DMA*-SH achieves zero-shot generalization, outperforming domain randomization by 58.1% and surpassing a standard context-aware baseline by 11.5% on average.

cs.LG↗

arXiv2025

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

Real-world reinforcement learning demands adaptation to unseen environmental conditions without costly retraining. Contextual Markov Decision Processes (cMDP) model this challenge, but existing methods often require explicit context variables (e.g., friction, gravity), limiting their use when contexts are latent or hard to measure. We introduce Dynamics-Aligned Latent Imagination (DALI), a framework integrated within the Dreamer architecture that infers latent context representations from agent-environment interactions. By training a self-supervised encoder to predict forward dynamics, DALI generates actionable representations conditioning the world model and policy, bridging perception and control. We theoretically prove this encoder is essential for efficient context inference and robust generalization. DALI's latent space enables counterfactual consistency: Perturbing a gravity-encoding dimension alters imagined rollouts in physically plausible ways. On challenging cMDP benchmarks, DALI achieves significant gains over context-unaware baselines, often surpassing context-aware baselines in extrapolation tasks, enabling zero-shot generalization to unseen contextual variations.

cs.LG↗