4 papers
FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies
Sara Taheri, Deep Kumar Ganguly, Jan Křetínský +1
Even a few action perturbations can substantially degrade the performance of a deployed decision policy. Certifying the resulting return loss is challenging in stochastic environme…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
Deep Kumar Ganguly, Jan Křetínský
An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity--…
Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making
Deep Kumar Ganguly, Jan Kretinsky
How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties caution to epistemic uncertainty:…
The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning
Deep Kumar Ganguly, Chandradithya S Jonnalagadda, Pratham Chintamani +1
Cooperative equilibria are fragile. When agents learn alongside each other rather than in a fixed environment, the process of learning destabilizes the cooperation they are trying…