Author

Saunak Kumar Panda

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Nonparametric Variance-Penalized Actor-Critic: Statistical Inference for Risk-Sensitive Reinforcement Learning

This work proposes a nonparametric variance-penalized actor-critic (VPAC) framework that replaces the variance critic with statistically grounded online estimators based on bootstrapping and random scaling, techniques drawn from the statistical inference literature for stochastic approximation.

Saunak Kumar Panda, Tong Li, Yi-Sha Xiang et al. · 0 citations

#machine learning Preprint Sep 2026

Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations

This paper proposes an empirical method that improves certified lower bounds by selecting the training risk-aversion parameter $\beta$ independently of the risk level used during evaluation, and formulate the risk-sensitive certification problem as a convex optimization and derive its dual to obtain a tractable approxi...

Tong Li, Saunak Kumar Panda, Yi-Sha Xiang · 0 citations