Introduces post-hoc robustification of model-based RL agents via adversarial model-predictive control at inference time to improve robustness in perturbed environments without additional neural network training.
https://math.stackexchange.com/q/3613688 , URL =
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
-
Post-Hoc Robustness for Model-Based Reinforcement Learning
Introduces post-hoc robustification of model-based RL agents via adversarial model-predictive control at inference time to improve robustness in perturbed environments without additional neural network training.