SALSA-RL introduces latent-space stability analysis for actions of pretrained RL agents using encoder-decoder and state-dependent linear dynamics to enable non-invasive interpretability.
Toward physics-guided safe deep reinforcement learning for green data center cooling control
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning
SALSA-RL introduces latent-space stability analysis for actions of pretrained RL agents using encoder-decoder and state-dependent linear dynamics to enable non-invasive interpretability.