Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty

no code implementations • 5 Aug 2021 • Reazul Hasan Russel, Mouhacine Benosman, Jeroen van Baar, Radu Corcodel

Safety and robustness are two desired properties for any reinforcement learning algorithm.

reinforcement-learning Reinforcement Learning (RL)

Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty

1 code implementation • 10 Oct 2020 • Reazul Hasan Russel, Mouhacine Benosman, Jeroen van Baar

In this paper, we focus on the problem of robustifying reinforcement learning (RL) algorithms with respect to model uncertainties.

Management Reinforcement Learning (RL)

Entropic Risk Constrained Soft-Robust Policy Optimization

no code implementations • 20 Jun 2020 • Reazul Hasan Russel, Bahram Behzadian, Marek Petrik

Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs

no code implementations • 4 Dec 2019 • Reazul Hasan Russel, Bahram Behzadian, Marek Petrik

Our proposed method computes a weight parameter from the value functions, and these weights then drive the shape of the ambiguity sets.

A Probabilistic Approach to Satisfiability of Propositional Logic Formulae

no code implementations • 4 Dec 2019 • Reazul Hasan Russel

We propose a version of WalkSAT algorithm, named as BetaWalkSAT.

Optimizing Percentile Criterion Using Robust MDPs

no code implementations • 23 Oct 2019 • Bahram Behzadian, Reazul Hasan Russel, Marek Petrik, Chin Pang Ho

We then propose new algorithms that minimize the span of ambiguity sets defined by weighted $L_1$ and $L_\infty$ norms.

Reinforcement Learning (RL)

A Short Survey on Probabilistic Reinforcement Learning

no code implementations • 21 Jan 2019 • Reazul Hasan Russel

A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment.

reinforcement-learning Reinforcement Learning (RL)

Tight Bayesian Ambiguity Sets for Robust MDPs

no code implementations • 15 Nov 2018 • Reazul Hasan Russel, Marek Petrik

Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters.

Decision Making Reinforcement Learning (RL)

Value Directed Exploration in Multi-Armed Bandits with Structured Priors

no code implementations • 12 Apr 2017 • Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml

Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation.

Multi-Armed Bandits