Alex Ayoub

6 papers · 2020–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14)

Venues

ICML (3) NeurIPS (2) AISTATS (1)

Top co-authors

Csaba Szepesvári (4) Shuai Liu (2) Lin Yang (2) Doina Precup (1) Kaiwen Wang (1) Francesco Zanini (1) Masood Dehghan (1) David Janz (1) Zhaoran Wang (1) Zichen (Vincent) Zhang (1)

Research topics

Machine Learning (5) Reinforcement Learning (5) Methods (4) Optimization & Theory (4) Learning Types (3) Artificial Intelligence (2) Mathematics & Optimization (2) Applications (2) Optimization (2) Core AI (1) Learning Paradigms (1) Mathematics (1) Probability (1)

Keywords

regret bound (2) generalized linear bandit (2) policy evaluation (1) regret minimization (1) value function (1) exponential family (1) fitted q-iteration (1) multi-armed bandit (1) value function approximation (1) batch reinforcement learning (1) log loss (1) value estimation (1) optimistic exploration (1) thompson sampling (1) eluder dimension (1) model-based reinforcement learning (1) episodic learning (1) optimistic algorithm (1) stochastic bandit (1) reinforcement learning (1)

Papers

Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits NeurIPS 2024 Exploration via linearly perturbed loss minimisation AISTATS 2024 Switching the Loss Reduces the Cost in Batch Reinforcement Learning ICML 2024 Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off NeurIPS 2023 Randomized Exploration in Reinforcement Learning with General Value Function Approximation ICML 2021 Model-Based Reinforcement Learning with Value-Targeted Regression ICML 2020