19 citations · 40 across the 13 of their papers we have counts for
12 papers · 1 filter
DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction
Reazul Hasan Russel, Mingwei Tang, Rostam Shirani +18
Offsite conversion rate (OCVR) prediction is an important ranking problem in computational recommendation systems. This task presents a modeling challenge: click signals are abunda…
RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk
Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh +1
Prior work on safe Reinforcement Learning (RL) has studied risk-aversion to randomness in dynamics (aleatory) and to model uncertainty (epistemic) in isolation. We propose and anal…
Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty
Reazul Hasan Russel, Mouhacine Benosman, Jeroen Van Baar +1
Safety and robustness are two desired properties for any reinforcement learning algorithm. CMDPs can handle additional safety constraints and RMDPs can perform well under model unc…
Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty
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. Indeed, in the framework of model-based RL, we pr…
Entropic Risk Constrained Soft-Robust Policy Optimization
Reazul Hasan Russel, Bahram Behzadian, Marek Petrik
Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by mo…
Optimizing Norm-Bounded Weighted Ambiguity Sets for Robust MDPs
Reazul Hasan Russel, Bahram Behzadian, Marek Petrik
Optimal policies in Markov decision processes (MDPs) are very sensitive to model misspecification. This raises serious concerns about deploying them in high-stake domains. Robust M…
Optimizing Percentile Criterion Using Robust MDPs
Bahram Behzadian, Reazul Hasan Russel, Marek Petrik +1
We address the problem of computing reliable policies in reinforcement learning problems with limited data. In particular, we compute policies that achieve good returns with high c…
Robust Exploration with Tight Bayesian Plausibility Sets
Reazul H. Russel, Tianyi Gu, Marek Petrik
Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism…
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs
Marek Petrik, Reazul Hasan Russell
Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by…
A Short Survey on Probabilistic Reinforcement Learning
Reazul Hasan Russel
A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well…
Tight Bayesian Ambiguity Sets for Robust MDPs
Reazul Hasan Russel, Marek Petrik
Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMD…
Value Directed Exploration in Multi-Armed Bandits with Structured Priors
Bence Cserna, Marek Petrik, Reazul Hasan Russel +1
Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms wi…