Name: Reinforcement Learning for Stochastic Networks, Toulouse
Start: 2024-06-17T09:00:00+02:00
End: 2024-06-21T18:00:00+02:00
Location: ENSEEIHT

Reinforcement Learning for Stochastic Networks, Toulouse

from Monday, June 17, 2024 (9:00 AM) to Friday, June 21, 2024 (6:00 PM)

Monday, June 17, 2024

10:00 AM Coffee
Coffee
10:00 AM - 10:45 AM
Room: B006 – B007

10:45 AM

10:45 AM - 11:00 AM
Room: Amphi B00
11:00 AM
11:00 AM - 12:00 PM
Room: Amphi B00
Contributions

11:00 AM Learning and Control in Countable State Spaces
12:00 PM Lunch
Lunch
12:00 PM - 1:30 PM
Room: C101-C103
1:30 PM
1:30 PM - 3:00 PM
Room: A002
Contributions

1:30 PM Exploiting Structure in Undiscounted Reinforcement Learning in Markov Decision Processes - Ronald Ortner (MontanUniversitat Leoben)

2:00 PM Exploration in reward machines with near-optimal regret - Mohammad Sadegh Talebi (University of Copenhagen)

2:30 PM Provably Efficient Offline Reinforcement Learning in Regular Decision Processes - Anders Jonsson (University Pompeu Fabra)
1:30 PM - 3:00 PM
Room: A001
Contributions

1:30 PM Computing the bias of stochastic approximation with constant step-size via Stein's method. - Nicolas Gast (Inria, Univ. Grenoble Alpes)

2:00 PM Convergence for Natural Policy Gradient on Infinite-State Average-Reward Markov Decision Processes - Isaac Grosof (University of Illinois, Urbana-Champaign; Northwestern University)

2:30 PM On the Global Convergence of Policy Based Methods in Average Reward Problems - Yashaswini Murthy (University of Illinois Urbana Champaign)
3:00 PM Coffee break
Coffee break
3:00 PM - 3:30 PM
Room: B006-B007
3:30 PM
3:30 PM - 5:00 PM
Room: A002
Contributions

3:30 PM Online Learning and Optimization for Queues with Unknown Demand Curve and Service Distribution - Xinyun Chen (The Chinese University of Hong Kong, Shenzhen)

4:00 PM Recent Advances in Average-Reward Restless Bandits - Weina Wang (Carnegie Mellon University)

4:30 PM Scalable Learning in Weakly Coupled Markov Decision Processes - Chen Yan
3:30 PM - 5:00 PM
Room: A001
Contributions

3:30 PM Optimized Decision Making via Active Learning of Stochastic Hamiltonians - Chandrajit Bajaj (UT Austin)

4:00 PM Simulation Optimization of Reflected Diffusion Processes - Harsha Honnappa (Purdue University)

4:30 PM Symphony of experts: orchestration with adversarial insights in reinforcement learning - Chiara Mignacco (Université Paris-Saclay)
Tuesday, June 18, 2024
9:30 AM
9:30 AM - 10:30 AM
Room: Amphi B00
Contributions

9:30 AM Finite Sample analysis of linear stochastic approximation and TD learning
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
Room: B006-B007
11:00 AM
11:00 AM - 12:00 PM
Room: Amphi B00
Contributions

11:00 AM Exploiting Structure In Reinforcement Learning
12:00 PM Lunch
Lunch
12:00 PM - 1:30 PM
Room: C101-C103
1:30 PM
1:30 PM - 3:00 PM
Room: A002
Contributions

1:30 PM The Traveling Salesman Problem: Novel Approaches Grounded in Evolutionary Reinforcement Learning - SAFA BHAR LAYEB (LR-OASIS National Engineering School of Tunis, University of Tunis El Manar, Tunis, Tunisia)

2:00 PM Scalable Policies for the Dynamic Traveling Multi-Maintainer Problem with Alerts - Peter Verleijsdonk (Eindhoven University of Technology)

2:30 PM Fleming-Viot particle systems to accelerate optimal policy learning in the presence of costly rare events - Daniel Mastropietro (INP Toulouse, CNRS-IRIT)
1:30 PM - 3:00 PM
Room: A001
Contributions

1:30 PM Joint learning and scheduling in queueing systems - Lei Ying (University of Michigan, Ann Arbor)

2:00 PM Neural Inventory Control in Networks via Hindsight Differentiable Policy Optimization - Matias Alvo (Columbia Business School (Decision, Risk and Operations division))

2:30 PM A Doubly Robust Approach to Sparse Reinforcement Learning - Assaf Zeevi (columbia university)
3:00 PM
3:00 PM - 4:00 PM
Room: Hall of building C
Contributions

3:00 PM Boosting Rare Event Simulation in Markov Processes - Ernesto Garcia (LAAS)

3:00 PM Time-Constrained Robust MDPs - Adil Zouitine (SUPAERO)

3:00 PM Reinforcement learning and regret bounds for admission control - Lucas Weber (Inria)

3:00 PM Learning payoffs while routing in skill-based queues - Sanne van Kempen (TU/e)

3:00 PM Dynamic Scheduling and Trajectory Planning for Urban Intersections with Heterogeneous Autonomous Traffic - Purva Joshi (TU/e)

3:00 PM Non-preemptive scheduling with non-observable environment - Thomas Hira (IRIT)
4:00 PM
4:00 PM - 5:30 PM
Room: A002
Contributions

4:00 PM Backlogged Bandits for Network Utility Maximization - Juaren Steiger (Queen's University)

4:30 PM Interpersonal trust: An asymptotic analysis of a stochastic coordination game with multi-agent learning - Benedikt Meylahn (Korteweg-de Vries Institute for Mathematics, University of Amsterdam)

5:00 PM Multiagent Q-learning with `satisficing' criteria - Vivek Borkar (Indian Institute of Technology Bombay)
4:00 PM - 5:30 PM
Room: A001
Contributions

4:00 PM Stability and performance of multi-class queueing systems with unknown service rates: A combined scheduling-learning approach - Elene Anton (Université de Pau et des Pays de l'Adour (UPPA))

4:30 PM Dynamic Scheduling of a Multiclass Queue in the Halfin-Whitt Regime: A Computational Approach for High-Dimensional Problems - Ebru Kasikaralar (University of Chicago Booth School of Business)

5:00 PM Designing M/G/1 Scheduling Policies from Job Size Samples - Shefali Ramakrishna (Cornell University)
6:00 PM

6:00 PM - 7:30 PM
Wednesday, June 19, 2024
9:30 AM
9:30 AM - 10:30 AM
Room: Amphi B00
Contributions

9:30 AM Learning Augmented Algorithms for MDPs
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
Room: B006-B007
11:00 AM
11:00 AM - 12:00 PM
Room: Amphi B00
Contributions

11:00 AM Inpatient Overflow Management with Proximal Policy Optimization
12:00 PM Lunch
Lunch
12:00 PM - 1:30 PM
Room: C101-C103
1:30 PM
1:30 PM - 3:00 PM
Room: A002
Contributions

1:30 PM Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data - Kishan Panaganti (California Institute of Technology)

2:00 PM Score-Aware Policy-Gradient Methods and Performance Guarantees using Local Lyapunov Conditions - Albert Senen–Cerda (IRIT, LAAS–CNRS, and Université de Toulouse)

2:30 PM Tabular and Deep Reinforcement learning for Gittins Index - Tejas Bodas (IIIT Hyderabad)
1:30 PM - 3:00 PM
Room: A001
Contributions

1:30 PM Learning LP-indices in Average-Reward Restless Multi-Armed Bandits - Konstantin Avrachenkov (INRIA Sophia Antipolis)

2:00 PM Optimal congestion signaling under customer heterogeneity with private types - Prakirt Jhunjhunwala (Columbia Business School)

2:30 PM Energy Management in Smart Grids Using Finite Horizon SOR Q-learning - Shalabh Bhatnagar (Indian Institute of Science)
Thursday, June 20, 2024
9:30 AM
9:30 AM - 10:30 AM
Room: Amphi B00
Contributions

9:30 AM Generalization in deep reinforcement learning and the role of representation learning for sequential decision-making tasks
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
Room: B006-B007
11:00 AM
11:00 AM - 12:00 PM
Room: Amphi B00
Contributions

11:00 AM The sliding regret
12:00 PM Lunch
Lunch
12:00 PM - 1:30 PM
Room: C101-C103
1:30 PM
1:30 PM - 3:00 PM
Room: A001
Contributions

1:30 PM Reinforcement learning in a prisoner's dilemma - Artur Dolgopolov (Bielefeld University)

2:00 PM Less than meets the eye: simultaneous experiments as a source of algorithmic seeming collusion - Xavier Lambin (ESSEC Business School)

2:30 PM Quantifying the likelihood of collusion by provably convergent reinforcement learning - Janusz Meylahn (University of Twente)
1:30 PM - 3:00 PM
Room: A002
Contributions

1:30 PM Decentralized MARL and Preference Learning: Balancing Grid Efficiency and Privacy in Demand Response - Jochen Cremer (Delft University of Technology)

2:00 PM Multi-Agent Reinforcement Learning for Power Grid Topology Optimization - Erica van der Sar (Vrije Universiteit Amsterdam)

2:30 PM Scalable Grid Topology Reconfiguration using Consensus-Based Multi Agent Reinforcement Learning - Barbera de Mol (University of Groningen/TenneT TSO (NED))
3:00 PM Coffee break
Coffee break
3:00 PM - 3:30 PM
Room: B006-B007
3:30 PM
3:30 PM - 5:00 PM
Room: A002
Contributions

3:30 PM Matching Impatient and Heterogeneous Demand and Supply while Learning - Amy Ward (The University of Chicago Booth)

4:00 PM Pseudo-Bayesian Optimization - Haoxian Chen (Columbia University)

4:30 PM Artificial Replay: How to get the most out of your data - Siddhartha Banerjee (Cornell University)
3:30 PM - 5:00 PM
Room: A001
Contributions

3:30 PM Instability and stability of parameter agnostic policies in parallel server systems - Yuan Zhong (University of Chicago)

4:00 PM Learning payoffs while routing in skill-based queues - Sanne van Kempen (Eindhoven University of Technology)

4:30 PM Online Load Balancing and Auto Scaling: Stochastic approximation algorithms for LP-based policy - Lucas Lopes (UFRJ) Alexandre Reiffers (IMT Atlantique)
Friday, June 21, 2024
9:30 AM
9:30 AM - 10:30 AM
Room: Amphi B00
Contributions

9:30 AM Lipschitz Lifelong Reinforcement Learning: transferring value functions across MDPs
10:30 AM Coffee break
Coffee break
10:30 AM - 11:00 AM
Room: B006-B007
11:00 AM
11:00 AM - 12:30 PM
Room: A001
Contributions

11:00 AM Non-Stationary Gradient Descent for Optimal Auto-Scaling in Serverless Platforms - Bruno Gaujal (Inria)

11:30 AM A Deep-Learning Approach to High-Dimensional Impulse Control with Applications to Inventory Management - Wouter Johannes van Eekelen (University of Chicago, Booth School of Business)

12:00 PM Using Reinforcement and Optimization for grid operation - A solution to the L2PRN 23 competition - Nicolas Lair (Artelys)
11:00 AM - 12:30 PM
Room: A002
Contributions

11:00 AM Achieving Regular and Fair Learning in Combinatorial Multi-Armed Bandit - Bin Li (Pennsylvania State University)

11:30 AM Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks - Jian Li (Stony Brook University)

12:00 PM Multi-Agent Reinforcement Learning for Collaborative Decision-Making in Network Optimization - Tian Lan (George Washington University)
12:30 PM Lunch
Lunch
12:30 PM - 2:00 PM
Room: C101-C103
2:00 PM
2:00 PM - 3:00 PM
Room: Amphi B00
Contributions

2:00 PM The Projected Bellman Equation in Reinforcement Learning

Choose timezone