6 papers
Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees
Yaacov Pariente, Vadim Indelman
Online POMDP planners optimize the expected cumulative cost, which can mask dangerous states when the belief places significant mass on high-cost states. Existing risk-averse metho…
Accelerated Online Risk-Averse Policy Evaluation in POMDPs with Theoretical Guarantees and Novel CVaR Bounds
Yaacov Pariente, Vadim Indelman
Risk-averse decision-making under uncertainty in partially observable domains is a central challenge in artificial intelligence and is essential for developing reliable autonomous…
POMDPPlanners: Open-Source Package for POMDP Planning
Yaacov Pariente, Vadim Indelman
We present POMDPPlanners, an open-source Python package for empirical evaluation of Partially Observable Markov Decision Process (POMDP) planning algorithms. The package integrates…
Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function
Yaacov Pariente, Vadim Indelman
We study risk-sensitive planning under partial observability using the dynamic risk measure Iterated Conditional Value-at-Risk (ICVaR). A policy evaluation algorithm for ICVaR is d…
Bounding Conditional Value-at-Risk via Auxiliary Distributions with Bounded Discrepancies
Yaacov Pariente, Vadim Indelman
In this paper, we develop a theoretical framework for bounding the CVaR of a random variable using another related random variable , under assumptions on their cumulative an…
Simplification of Risk Averse POMDPs with Performance Guarantees
Yaacov Pariente, Vadim Indelman
Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem…