DMA*-SH enables zero-shot generalization in contextual RL under discontinuous dynamics shifts by sharing hypernetwork-generated adapters across components, outperforming baselines on a new Actuator Inversion Benchmark.
In DMA*-SH, this cosine tracks whether the (hypothetical) reward-driven direction in the sharedη coordinates tends to align with or oppose the dynamics-driven direction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamics-Aligned Shared Hypernetworks for Contextual RL under Discontinuous Shifts
DMA*-SH enables zero-shot generalization in contextual RL under discontinuous dynamics shifts by sharing hypernetwork-generated adapters across components, outperforming baselines on a new Actuator Inversion Benchmark.