Portrait of Kaustubh Mani is unavailable

Kaustubh Mani

PhD - Université de Montréal
Supervisor
Liam Paull
Research Topics
Reinforcement Learning
Google Scholar
GitHub

Publications

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
Kaustubh Mani
Yann Pequignot
Vincent Mai
Liam Paull
Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach s… (see more)afe exploration through the lens of epistemic uncertainty, where the actor’s sensitivity to parameter perturbations serves as a practical proxy for regions of high uncertainty. We propose Sharpness-Aware Policy Optimization (SHAPO), a sharpness-aware policy update rule that evaluates gradients at perturbed parameters, making policy updates pessimistic with respect to the actor’s epistemic uncertainty. Analytically we show that this adjustment implicitly reweighs policy gradients, amplifying the influence of rare unsafe actions while tempering contributions from already safe ones, thereby biasing learning toward conservative behavior in under-explored regions. Across several continuous-control tasks, our method consistently improves both safety and task performance over existing baselines, significantly expanding their Pareto frontiers.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net
Safety Representations for Safer Policy Learning
Kaustubh Mani
Vincent Mai
Charlie Gauthier
Annie Chen
Samer Nashed
Liam Paull
Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safet… (see more)y-critical applications, the risks associated with such exploration can lead to catastrophic consequences. Existing safe exploration methods attempt to mitigate this by imposing constraints, which often result in overly conservative behaviours and inefficient learning. Heavy penalties for early constraint violations can trap agents in local optima, deterring exploration of risky yet high-reward regions of the state space. To address this, we introduce a method that explicitly learns state-conditioned safety representations. By augmenting the state features with these safety representations, our approach naturally encourages safer exploration without being excessively cautious, resulting in more efficient and safer policy learning in safety-critical scenarios. Empirical evaluations across diverse environments show that our method significantly improves task performance while reducing constraint violations during training, underscoring its effectiveness in balancing exploration with safety.
2025-01-21
ICLR.cc/2025/Conference (poster)
doi.org
openreview.net