Skip to yearly menu bar Skip to main content

Workshop

New Frontiers in Learning, Control, and Dynamical Systems

Valentin De Bortoli ⋅ Charlotte Bunne ⋅ Guan-Horng Liu ⋅ Tianrong Chen ⋅ Maxim Raginsky ⋅ Pratik Chaudhari ⋅ Melanie Zeilinger ⋅ Animashree Anandkumar

Project Page

Abstract

Recent advances in algorithmic design and principled, theory-driven deep learning architectures have sparked a growing interest in control and dynamical system theory. Complementary, machine learning plays an important role in enhancing existing control theory algorithms in terms of performance and scalability. The boundaries between both disciplines are blurring even further with the rise of modern reinforcement learning, a field at the crossroad of data-driven control theory and machine learning. This workshop aims to unravel the mutual relationship between learning, control, and dynamical systems and to shed light on recent parallel developments in different communities. Strengthening the connection between learning and control will open new possibilities for interdisciplinary research areas.

Video

Chat is not available.

Schedule

Timezone: Asia/Seoul

4:00 AM

On optimal control and machine learning

Brandon Amos

4:45 AM

Two-for-one: diffusion models and force fields for coarse-grained molecular dynamics

Rianne van den Berg

5:30 AM

Transport, VI, and Diffusions

Francisco Vargas ⋅ Nikolas Nüsken

Video

5:45 AM

Imposing and learning structure in OT displacements through cost engineering

Marco Cuturi

Video

6:30 AM

Designing High-Dimensional Closed-Loop Optimal Control Using Deep Neural Networks

Jiequn Han

Video

8:45 AM

Safe Learning in Control

Claire Tomlin

9:30 AM

Bridging RL Theory and Practice with the Effective Horizon

Cassidy Laidlaw ⋅ Stuart Russell ⋅ Anca Dragan

Video

10:00 AM

Reinforcement Learning and Multi-Agent Reinforcement Learning

Giorgia Ramponi

10:45 AM

Modeling Accurate Long Rollouts with Temporal Neural PDE Solvers

Phillip Lippe ⋅ Bastiaan Veeling ⋅ Paris Perdikaris ⋅ Richard E Turner ⋅ Johannes Brandstetter

Video

Analyzing the Sample Complexity of Model-Free Opponent Shaping

Kitty Fung ⋅ Qizhen Zhang ⋅ Christopher Lu ⋅ Timon Willi ⋅ Jakob Foerster

A Best Arm Identification Approach for Stochastic Rising Bandits

Alessandro Montenegro ⋅ Marco Mussi ⋅ Francesco Trovò ⋅ Marcello Restelli ⋅ Alberto Maria Metelli

Tendiffpure: Tensorizing Diffusion Models for Purification

Zhou Derun ⋅ Mingyuan Bai ⋅ Qibin Zhao

Continuous Vector Quantile Regression

Sanketh Vedula ⋅ Irene Tallini ⋅ Aviv A. Rosenberg ⋅ Marco Pegoraro ⋅ Emanuele Rodola ⋅ Yaniv Romano ⋅ Alexander Bronstein

Informed POMDP: Leveraging Additional Information in Model-Based RL

Gaspard Lambrechts ⋅ Adrien Bolland ⋅ Damien Ernst

Embedding Surfaces by Optimizing Neural Networks with Prescribed Riemannian Metric and Beyond

Yi Feng ⋅ Sizhe Li ⋅ Ioannis Panageas ⋅ Xiao Wang

Taylor TD-learning

Michele Garibbo ⋅ Maxime Robeyns ⋅ Laurence Aitchison

Toward Understanding Latent Model Learning in MuZero: A Case Study in Linear Quadratic Gaussian Control

Yi Tian ⋅ Kaiqing Zhang ⋅ Russ Tedrake ⋅ Suvrit Sra

Balancing exploration and exploitation in Partially Observed Linear Contextual Bandits via Thompson Sampling

Hongju Park ⋅ Mohamad Kazem Shirani Faradonbeh

Leveraging Factored Action Spaces for Off-Policy Evaluation

Aaman Rebello ⋅ Shengpu Tang ⋅ Jenna Wiens ⋅ Sonali Parbhoo

Diffusion Model-Augmented Behavioral Cloning

Hsiang-Chun Wang ⋅ Shang-Fu Chen ⋅ Ming-Hao Hsu ⋅ Chun-Mao Lai ⋅ Shao-Hua Sun

Unbalanced Diffusion Schrödinger Bridge

Matteo Pariset ⋅ Ya-Ping Hsieh ⋅ Charlotte Bunne ⋅ Andreas Krause ⋅ Valentin De Bortoli

Aligned Diffusion Schrödinger Bridges

Vignesh Ram Somnath ⋅ Matteo Pariset ⋅ Ya-Ping Hsieh ⋅ Maria Rodriguez Martinez ⋅ Andreas Krause ⋅ Charlotte Bunne

Dynamic Feature-based Newsvendor

Zexing Xu ⋅ Ziyi Chen ⋅ Xin Chen

Equivalence Class Learning for GENERIC Systems

Baige Xu ⋅ Yuhan Chen ⋅ Takashi Matsubara ⋅ Takaharu Yaguchi

Variational Principle and Variational Integrators for Neural Symplectic Forms

Yuhan Chen ⋅ Baige Xu ⋅ Takashi Matsubara ⋅ Takaharu Yaguchi

Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning

Xinyang Lu ⋅ Xiaofeng Fan ⋅ Tianying Wang

Accelerated Policy Gradient: On the Nesterov Momentum for Reinforcement Learning

Yen-Ju Chen ⋅ Nai-Chieh Huang ⋅ Ping-Chun Hsieh

Exponential weight averaging as damped harmonic motion

Jonathan Patsenker ⋅ Henry Li ⋅ Yuval Kluger

Algorithms for Optimal Adaptation of Diffusion Models to Reward Functions

Krishnamurthy Dvijotham ⋅ Shayegan Omidshafiei ⋅ Kimin Lee ⋅ Katie Collins ⋅ Deepak Ramachandran ⋅ Adrian Weller ⋅ Mohammad Ghavamzadeh ⋅ Milad Nasresfahani ⋅ Ying Fan ⋅ Jeremiah Liu

On learning history-based policies for controlling Markov decision processes

Gandharv Patil ⋅ Aditya Mahajan ⋅ Doina Precup

Visual Dexterity: In-hand Dexterous Manipulation from Depth

Tao Chen ⋅ Megha Tippur ⋅ Siyang Wu ⋅ Vikash Kumar ⋅ Edward Adelson ⋅ Pulkit Agrawal

Learning from Sparse Offline Datasets via Conservative Density Estimation

Zhepeng Cen ⋅ Zuxin Liu ⋅ Zitong Wang ⋅ Yihang Yao ⋅ Henry Lam ⋅ Ding Zhao

Undo Maps: A Tool for Adapting Policies to Perceptual Distortions

Abhi Gupta ⋅ Ted Moskovitz ⋅ David Alvarez-Melis ⋅ Aldo Pacchiano

When is Agnostic Reinforcement Learning Statistically Tractable?

Gene Li ⋅ Zeyu Jia ⋅ Alexander Rakhlin ⋅ Ayush Sekhari ⋅ Nati Srebro

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport

Alexander Tong ⋅ Nikolay Malkin ⋅ Guillaume Huguet ⋅ Yanlei Zhang ⋅ Jarrid Rector-Brooks ⋅ Kilian Fatras ⋅ Guy Wolf ⋅ Yoshua Bengio

In-Context Decision-Making from Supervised Pretraining

Jonathan Lee ⋅ Annie Xie ⋅ Aldo Pacchiano ⋅ Yash Chandak ⋅ Chelsea Finn ⋅ Ofir Nachum ⋅ Emma Brunskill

Statistics estimation in neural network training: a recursive identification approach

Ruth Crasto ⋅ Xuchan Bao ⋅ Roger Grosse

Learning to Optimize with Recurrent Hierarchical Transformers

Abhinav Moudgil ⋅ Boris Knyazev ⋅ Guillaume Lajoie ⋅ Eugene Belilovsky

Fixed-Budget Hypothesis Best Arm Identification: On the Information Loss in Experimental Design

Masahiro Kato ⋅ Masaaki Imaizumi ⋅ Takuya Ishihara ⋅ Toru Kitagawa

Unbalanced Optimal Transport meets Sliced-Wasserstein

Thibault Sejourne ⋅ Clément Bonet ⋅ Kilian Fatras ⋅ Kimia Nadjahi ⋅ Nicolas Courty

Improved sampling via learned diffusions

Julius Berner ⋅ Lorenz Richter ⋅ Guan-Horng Liu

Stability of Multi-Agent Learning: Convergence in Network Games with Many Players

Aamal Hussain ⋅ Dan Leonte ⋅ Francesco Belardinelli ⋅ Georgios Piliouras

Limited Information Opponent Modeling

Yongliang Lv ⋅ Yan Zheng ⋅ jianye Hao

Game Theoretic Neural ODE Optimizer

Panagiotis Theodoropoulos ⋅ Guan-Horng Liu ⋅ Tianrong Chen ⋅ Evangelos Theodorou

A neural RDE approach for continuous-time non-Markovian stochastic control problems

Melker Höglund ⋅ Emilio Ferrucci ⋅ Camilo Hernández ⋅ Aitor Muguruza Gonzalez ⋅ Cristopher Salvi ⋅ Leandro Sánchez-Betancourt ⋅ Yufei Zhang

On First-Order Meta-Reinforcement Learning with Moreau Envelopes

Mohammad Taha Toghani ⋅ Sebastian Perez-Salazar ⋅ Cesar Uribe

Vector Quantile Regression on Manifolds

Marco Pegoraro ⋅ Sanketh Vedula ⋅ Aviv A. Rosenberg ⋅ Irene Tallini ⋅ Emanuele Rodola ⋅ Alexander Bronstein

Learning with Learning Awareness using Meta-Values

Tim Cooijmans ⋅ Milad Aghajohari ⋅ Aaron Courville

Kernel Mirror Prox and RKHS Gradient Flow for Mixed Functional Nash Equilibrium

Pavel Dvurechenskii ⋅ Jia-Jie Zhu

Simulation-Free Schrödinger Bridges via Score and Flow Matching

Alexander Tong ⋅ Nikolay Malkin ⋅ Kilian Fatras ⋅ Lazar Atanackovic ⋅ Yanlei Zhang ⋅ Guillaume Huguet ⋅ Guy Wolf ⋅ Yoshua Bengio

Latent Space Editing in Transformer-Based Flow Matching

Tao Hu ⋅ David Zhang ⋅ Meng Tang ⋅ Pascal Mettes ⋅ Deli Zhao ⋅ Cees Snoek

Structured State Space Models for In-Context Reinforcement Learning

Christopher Lu ⋅ Yannick Schroecker ⋅ Albert Gu ⋅ Emilio Parisotto ⋅ Jakob Foerster ⋅ Satinder Singh ⋅ Feryal Behbahani

Maximum State Entropy Exploration using Predecessor and Successor Representations

Arnav Kumar Jain ⋅ Lucas Lehnert ⋅ Irina Rish ⋅ Glen Berseth

PAC-Bayesian Bounds for Learning LTI-ss systems with Input from Empirical Loss

Deividas Eringis ⋅ john leth ⋅ Rafal Wisniewski ⋅ Zheng-Hua Tan ⋅ Mihaly Petreczky

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

Alizée Pace ⋅ Hugo Yèche ⋅ Bernhard Schölkopf ⋅ Gunnar Ratsch ⋅ Guy Tennenholtz

Preventing Reward Hacking with Occupancy Measure Regularization

Cassidy Laidlaw ⋅ Shivam Singhal ⋅ Anca Dragan

Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures

Hao Liang ⋅ Zhi-Quan Luo

AbODE: Ab initio antibody design using conjoined ODEs

Yogesh Verma ⋅ Markus Heinonen ⋅ Vikas K Garg

Randomized methods for computing optimal transport without regularization and their convergence analysis

Yue Xie ⋅ Zhongjian Wang ⋅ Zhiwen Zhang

Sub-linear Regret in Adaptive Model Predictive Control

Damianos Tranos ⋅ Alexandre Proutiere

Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation

Qiwen Cui ⋅ Kaiqing Zhang ⋅ Simon Du

Offline Goal-Conditioned RL with Latent States as Actions

Seohong Park ⋅ Dibya Ghosh ⋅ Benjamin Eysenbach ⋅ Sergey Levine

Variational quantum dynamics of two-dimensional rotor models

Matija Medvidović ⋅ Dries Sels

Sample Complexity of Hierarchical Decompositions in Markov Decision Processes

Arnaud Robert ⋅ Ciara Pike-Burke ⋅ Aldo Faisal

Boosting Off-policy RL with Policy Representation and Policy-extended Value Function Approximator

Min Zhang ⋅ Jianye Hao ⋅ Hongyao Tang ⋅ Yan Zheng

Guide Your Agent with Adaptive Multimodal Rewards

Changyeon Kim ⋅ Younggyo Seo ⋅ Hao Liu ⋅ Lisa Lee ⋅ Jinwoo Shin ⋅ Honglak Lee ⋅ Kimin Lee

Neural Optimal Transport with Lagrangian Costs

Aram-Alexandre Pooladian ⋅ Carles Domingo i Enrich ⋅ Ricky T. Q. Chen ⋅ Brandon Amos

Deep Equilibrium Based Neural Operators for Steady-State PDEs

Tanya Marwah ⋅ Ashwini Pokle ⋅ Zico Kolter ⋅ Zachary Lipton ⋅ Jianfeng Lu ⋅ Andrej Risteski

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

PENG CHENG ⋅ Xianyuan Zhan ⋅ Zhihao Wu ⋅ Wenjia Zhang ⋅ Youfang Lin ⋅ Shou cheng Song ⋅ Han Wang

Nonlinear Wasserstein Distributionally Robust Optimal Control

Zhengang Zhong ⋅ Jia-Jie Zhu

Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models

Nicolò Botteghi ⋅ Federico Califano ⋅ University Twente ⋅ Christoph Brune

Coupled Gradient Flows for Strategic Non-Local Distribution Shift

Lauren Conger ⋅ Franca Hoffmann ⋅ Eric Mazumdar ⋅ Lillian Ratliff

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Minshuo Chen ⋅ Yu Bai ⋅ H. Vincent Poor ⋅ Mengdi Wang

LEAD: Min-Max Optimization from a Physical Perspective

Reyhane Askari Hemmat ⋅ Amartya Mitra ⋅ Guillaume Lajoie ⋅ Ioannis Mitliagkas

Stochastic Linear Bandits with Unknown Safety Constraints and Local Feedback

Nithin Varma ⋅ Sahin Lale ⋅ Anima Anandkumar

Distributional Distance Classifiers for Goal-Conditioned Reinforcement Learning

Ravi Tej Akella ⋅ Benjamin Eysenbach ⋅ Jeff Schneider ⋅ Ruslan Salakhutdinov

Taylorformer: Probabalistic Modelling for Random Processes including Time Series

Omer Nivron ⋅ Raghul Parthipan ⋅ Damon Wischik

Policy Gradient Algorithms Implicitly Optimize by Continuation

Adrien Bolland ⋅ Gilles Louppe ⋅ Damien Ernst

Randomly Coupled Oscillators for Time Series Processing

Andrea Ceni ⋅ Andrea Cossu ⋅ Jingyue Liu ⋅ Maximilian Stölzle ⋅ Cosimo Della Santina ⋅ Claudio Gallicchio ⋅ Davide Bacciu

On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions

Christopher Diehl ⋅ Tobias Klosek ⋅ Martin Krueger ⋅ Nils Murzyn ⋅ Torsten Bertram

Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning

Hanlin Zhu ⋅ Paria Rashidinejad ⋅ Jiantao Jiao

Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Markov Chains

Yilong Qin ⋅ Andrej Risteski

IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control

Yingchen Xu ⋅ Rohan Chitnis ⋅ Bobak Hashemi ⋅ Lucas Lehnert ⋅ Urun Dogan ⋅ Zheqing Zhu ⋅ Olivier Delalleau

Parallel Sampling of Diffusion Models

Andy Shih ⋅ Suneel Belkhale ⋅ Stefano Ermon ⋅ Dorsa Sadigh ⋅ Nima Anari

Fast Approximation of the Generalized Sliced-Wasserstein Distance

Dung Le ⋅ Huy Nguyen ⋅ Khai Nguyen ⋅ Nhat Ho

A Policy-Decoupled Method for High-Quality Data Augmentation in Offline Reinforcement Learning

Shixi Lian ⋅ Yi Ma ⋅ Jinyi Liu ⋅ Jianye Hao ⋅ Yan Zheng ⋅ Zhaopeng Meng

On the Generalization Capacities of Neural Controlled Differential Equations

Linus Bleistein ⋅ Agathe Guilloux

Factor Learning Portfolio Optimization Informed by Continuous-Time Finance Models

Sinong Geng ⋅ houssam nassif ⋅ Zhaobin Kuang ⋅ A. Max Reppen ⋅ Ronnie Sircar

Modular Hierarchical Reinforcement Learning for Robotics: Improving Scalability and Generalizability

Mihai Anca ⋅ Mark Hansen ⋅ Matthew Studley

Parameterized projected Bellman operator

Théo Vincent ⋅ Alberto Maria Metelli ⋅ Jan Peters ⋅ Marcello Restelli ⋅ Carlo D'Eramo

Improving Offline-to-Online Reinforcement Learning with Q-Ensembles

Kai Zhao ⋅ Yi Ma ⋅ Jinyi Liu ⋅ Jianye Hao ⋅ Yan Zheng ⋅ Zhaopeng Meng

Model-based Policy Optimization under Approximate Bayesian Inference

Chaoqi Wang ⋅ Yuxin Chen ⋅ Kevin Murphy

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Tony Zhao ⋅ Vikash Kumar ⋅ Sergey Levine ⋅ Chelsea Finn

On the Imitation of Non-Markovian Demonstrations: From Low-Level Stability to High-Level Planning

Adam Block ⋅ Daniel Pfrommer ⋅ Max Simchowitz

On Convergence of Approximate Schr\"{o}dinger Bridge with Bounded Cost

Wei Deng ⋅ Yu Chen ⋅ Tianjiao N Yang ⋅ Hengrong Du ⋅ Qi Feng ⋅ Ricky T. Q. Chen

Online Control with Adversarial Disturbance for Continuous-time Linear Systems

Jingwei Li ⋅ Jing Dong ⋅ Baoxiang Wang ⋅ Jingzhao Zhang

A Flexible Diffusion Model

weitao du ⋅ He Zhang ⋅ Tao Yang ⋅ Yuanqi Du

Synthetic Experience Replay

Cong Lu ⋅ Philip Ball ⋅ Yee-Whye Teh ⋅ Jack Parker-Holder

Fairness In a Non-Stationary Environment From an Optimal Control Perspective

Zhuotong Chen ⋅ Qianxiao Li ⋅ Zheng Zhang

Physics-informed Localized Learning for Advection-Diffusion-Reaction Systems

Surya Sathujoda ⋅ Soham Sheth

On the effectiveness of neural priors in modeling dynamical systems

Sameera Ramasinghe ⋅ Hemanth Saratchandran ⋅ Violetta Shevchenko ⋅ Simon Lucey

Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)

Amartya Mukherjee ⋅ Jun Liu

Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs

Amartya Mukherjee ⋅ Jun Liu

Optimization or Architecture: What Matters in Non-Linear Filtering?

Ido Greenberg ⋅ Netanel Yannay ⋅ Shie Mannor

Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversion

Lucas Böttcher

What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?

Songyang Han ⋅ Sanbao Su ⋅ Sihong He ⋅ Shuo Han ⋅ Haizhao Yang ⋅ Fei Miao