Accepted Paper

Our Frontier4LCD workshop has received 134 outstanding submissions, and we are thrilled to announce that 100 high-quality papers have been accepted for presentation. Below is the list of accepted papers.

Number Title
1 AbODE: Ab initio antibody design using conjoined ODEs
2 Distributional Distance Classifiers for Goal-Conditioned Reinforcement Learning
3 LEAD: Min-Max Optimization from a Physical Perspective
4 Balancing exploration and exploitation in Partially Observed Linear Contextual Bandits via Thompson Sampling
5 Stochastic Linear Bandits with Unknown Safety Constraints and Local Feedback
6 Visual Dexterity: In-hand Dexterous Manipulation from Depth
7 Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures
8 On learning history-based policies for controlling Markov decision processes
9 Improved sampling via learned diffusions
10 Fast Approximation of the Generalized Sliced-Wasserstein Distance
11 Synthetic Experience Replay
12 A neural RDE approach for continuous-time non-Markovian stochastic control problems
13 Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
14 Toward Understanding Latent Model Learning in MuZero: A Case Study in Linear Quadratic Gaussian Control
15 Gradient-free training of neural ODEs for system identification and control using ensemble Kalman inversion
16 Preventing Reward Hacking with Occupancy Measure Regularization
17 Exponential weight averaging as damped harmonic motion
18 Bridging RL Theory and Practice with the Effective Horizon
19 Accelerated Policy Gradient: On the Nesterov Momentum for Reinforcement Learning
20 Neural Optimal Transport with Lagrangian Costs
21 Taylor TD-learning
22 Coupled Gradient Flows for Strategic Non-Local Distribution Shift
23 Kernel Mirror Prox and RKHS Gradient Flow for Mixed Functional Nash Equilibrium
24 What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?
25 On the Generalization Capacities of Neural Controlled Differential Equations
26 A Best Arm Identification Approach for Stochastic Rising Bandits
27 Maximum State Entropy Exploration using Predecessor and Successor Representations
28 Guide Your Agent with Adaptive Multimodal Rewards
29 Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation
30 Unbalanced Optimal Transport meets Sliced-Wasserstein
31 Randomly Coupled Oscillators for Time Series Processing
32 Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
33 Boosting Off-policy RL with Policy Representation and Policy-extended Value Function Approximator
34 Statistics estimation in neural network training: a recursive identification approach
35 Embedding Surfaces by Optimizing Neural Networks with Prescribed Riemannian Metric and Beyond
36 Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
37 A Flexible Diffusion Model
38 Simulation-Free Schrödinger Bridges via Score and Flow Matching
39 On the Imitation of Non-Markovian Demonstrations: From Low-Level Stability to High-Level Planning
40 Fixed-Budget Hypothesis Best Arm Identification: On the Information Loss in Experimental Design
41 Variational Principle and Variational Integrators for Neural Symplectic Forms
42 A Policy-Decoupled Method for High-Quality Data Augmentation in Offline Reinforcement Learning
43 When is Agnostic Reinforcement Learning Statistically Tractable?
44 Algorithms for Optimal Adaptation ofDiffusion Models to Reward Functions
45 On Convergence of Approximate Schr\"{o}dinger Bridge with Bounded Cost
46 In-Context Decision-Making from Supervised Pretraining
47 Unbalanced Diffusion Schrödinger Bridge
48 Learning from Sparse Offline Datasets via Conservative Density Estimation
49 Parameterized projected Bellman operator
50 Randomized methods for computing optimal transport without regularization and their convergence analysis
51 Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)
52 On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions
53 Dynamic Feature-based Newsvendor
54 Game Theoretic Neural ODE Optimizer
55 Diffusion Model-Augmented Behavioral Cloning
56 Vector Quantile Regression on Manifolds
57 PAC-Bayesian Bounds for Learning LTI-ss systems with Input from Empirical Loss
58 Learning to Optimize with Recurrent Hierarchical Transformers
59 Sample Complexity of Hierarchical Decompositions in Markov Decision Processes
60 Fairness In a Non-Stationary Environment From an Optimal Control Perspective
61 Modular Hierarchical Reinforcement Learning for Robotics: Improving Scalability and Generalizability
62 Taylorformer: Probabalistic Modelling for Random Processes including Time Series
63 Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
64 Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport
65 Deep Equilibrium Based Neural Operators for Steady-State PDEs
66 Informed POMDP: Leveraging Additional Information in Model-Based RL
67 IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
68 Modeling Accurate Long Rollouts with Temporal Neural PDE Solvers
69 Sub-linear Regret in Adaptive Model Predictive Control
70 Analyzing the Sample Complexity of Model-Free Opponent Shaping
71 Continuous Vector Quantile Regression
72 Trajectory Generation, Control, and Safety with Denoising Diffusion Probabilistic Models
73 Structured State Space Models for In-Context Reinforcement Learning
74 Latent Space Editing in Transformer-Based Flow Matching
75 Transport, VI, and Diffusions
76 Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Markov Chains
77 Policy Gradient Algorithms Implicitly Optimize by Continuation
78 Improving Offline-to-Online Reinforcement Learning with Q-Ensembles
79 Offline Goal-Conditioned RL with Latent States as Actions
80 On the effectiveness of neural priors in modeling dynamical systems
81 Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning
82 Physics-informed Localized Learning for Advection-Diffusion-Reaction Systems
83 Factor Learning Portfolio Optimization Informed by Continuous-Time Finance Models
84 Equivalence Class Learning for GENERIC Systems
85 Model-based Policy Optimization under Approximate Bayesian Inference
86 Nonlinear Wasserstein Distributionally Robust Optimal Control
87 Online Control with Adversarial Disturbance for Continuous-time Linear Systems
88 Leveraging Factored Action Spaces for Off-Policy Evaluation
89 Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
90 Limited Information Opponent Modeling
91 Tendiffpure: Tensorizing Diffusion Models for Purification
92 Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
93 Optimization or Architecture: What Matters in Non-Linear Filtering?
94 Variational quantum dynamics of two-dimensional rotor models
95 Parallel Sampling of Diffusion Models
96 Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs
97 Undo Maps: A Tool for Adapting Policies to Perceptual Distortions
98 Learning with Learning Awareness using Meta-Values
99 Aligned Diffusion Schrödinger Bridges
100 On First-Order Meta-Reinforcement Learning with Moreau Envelopes