Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize trajectory optimization by means of a denoising autoencoder that is trained on the …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “optimization trajectory”
Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction and optimization. Interestingly, most all prior work in imitation and reinforcemen…
Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancycs.LG
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
problem Understanding the directional structure and redundancy in neural network optimization.
method Introducing natural notions of complexity for optimization trajectories and analyzing their directional nature.
result Training only scalar batchnorm parameters can match the performance of training the entire network, indicating potential for hybrid optimization schemes.
The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challengin…
Paper characterizes optimal learning trajectories for high-dimensional nonlinear models.
problem Characterizing optimal learning trajectories in high-dimensional nonlinear models.
method Exploits maximum principle and dynamic programming for an optimal control problem of a gradient system.
result Constructs optimal learning trajectories leading to optimal model parameters.
Study on Heisenberg group's Lorentzian problems using Pontryagin's principle.
problem Lorentzian problems on the Heisenberg group.
method Applied Pontryagin's maximum principle to obtain extremal trajectories.
result Parameterization of abnormal and normal extremal trajectories, investigation of reachability sets and existence of optimal trajectories.
Optimizes trading trajectories for large portfolios quickly.
problem Optimizing trading trajectories for large portfolios with constraints.
method Simulated bifurcation algorithm applied to portfolio optimization.
result First numerical results confirm SB algorithm's power for portfolio optimization.
Bayesian method estimates dynamics from near-optimal trajectories.
problem Estimating dynamics from near-optimal expert trajectories in reinforcement learning.
method Constraint-based Bayesian approach integrating expert near-optimality.
result Significant improvements in decision-making and transfer success.
End-to-end framework optimizes constrained trajectories using data-driven methods.
problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.
We study the tracking of a trajectory for a nonholonomic system by recasting the problem as a constrained optimal control problem. The cost function is chosen to minimize the error in positions and velocities between the trajectory of a nonholonomic system and the desired reference trajectory, both evolving on the dist…
New method improves learning from multiple correlated data trajectories.
problem Learning from multiple correlated data trajectories without mixing assumptions.
method Hellinger localization framework for maximum likelihood estimation.
result Instance-optimal bounds that scale with full data budget under broad conditions.
Paper finds optimal shapes for minimizing average lengths of billiard trajectories in specific polygons.
problem Finding optimal shapes to minimize the average length of billiard trajectories.
method Used techniques from Teichmüller theory.
result Optimal shapes minimize average lengths of billiard trajectories in specific polygons.
Develops a method to infer cell trajectories from RNA sequencing data.
problem Inferring cell trajectories from single cell RNA-sequencing data.
method Entropy-regularized optimal transport for global optimization.
result Proves and implements a method to recover ground truth trajectories from limited samples.
Optimal execution of portfolio transactions is the essential part of algorithmic trading. In this paper we present in simple analytical form the optimal trajectory for risk-averse trader with the assumption of exponential market recovery and short-time investment horizon.
Adaptive optimization methods bias neural network trajectories towards regions of lower local geometry.
problem The success of adaptive optimization methods in neural networks is not fully explained by traditional second-order methods.
method Local trajectory analysis and introduction of a new statistic .
result Adaptive methods like Adam bias trajectories towards regions of lower local geometry, leading to faster convergence.
The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations. In this article, we study this fundamental problem in the framework of energy-based model, where the observed expert trajectori…
Extends RL to random stopping times, improving optimization.
problem Real-world applications with random stopping times.
method Extended RL framework to random stopping times, derived new formulas.
result Improves optimization convergence with new formulas.
We present a novel clustering approach for moving object trajectories that are constrained by an underlying road network. The approach builds a similarity graph based on these trajectories then uses modularity-optimization hiearchical graph clustering to regroup trajectories with similar profiles. Our experimental stud…
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such sy…
New algorithm infers trajectories from partial observations using optimal transport.
problem Inferring trajectories from partial observations of coupled systems.
method Extends MFL algorithm to latent SDEs using observable state space models and partial observations.
result Experiments show significant outperformance over latent-free baseline.
This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.
problem Measuring and ranking uncertainty in multi-agent multi-modal trajectory forecasting.
method Proposes collaborative uncertainty (CU) and a CU-aware regression framework.
result The CU-aware regression framework improves SOTA systems' performances.
A new method learns straight trajectories in one step for optimal flow matching.
problem Learning flows with straight trajectories for fast inference.
method Optimal Flow Matching (OFM) approach using convex functions for vector fields.
result Recovering straight OT displacements in just one FM step for quadratic transport.
Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory fr…
The paper develops a new theory to understand deep learning optimization.
problem Understanding the dynamics of optimization in deep learning, especially in the edge of stability regime.
method Developed a central flow differential equation to describe the time-averaged trajectory of oscillatory optimizers.
result Central flows can predict long-term optimization trajectories with high numerical accuracy.
Trajectory-level supervision allows efficient offline reinforcement learning.
problem Offline reinforcement learning
method Developing a statistical theory for offline policy optimization from trajectory-level labels
result Proving a high-probability guarantee of order
A new reinforcement learning method reduces action complexity for robust control.
problem Deep reinforcement learning's susceptibility to spurious correlations.
method Minimizing trajectory entropy to encourage simple, predictable actions.
result Trajectory Entropy Reinforcement Learning achieves superior performance and robustness.
We consider in this paper the regularity problem for time-optimal trajectories of a single-input control-affine system on a n-dimensional manifold. We prove that, under generic conditions on the drift and the controlled vector field, any control u associated with an optimal trajectory is smooth out of a countable set o…
SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluationsstat.ML
SOCRATES uses LLMs to automate simulation optimization of complex systems.
problem Optimizing complex, expensive-to-sample stochastic systems.
method Two-stage procedure: replica construction and meta-optimization.
result Adaptive hybrid optimization schedule for real systems.
CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learningcs.LG
CEM-GD combines CEM and gradient descent for efficient model-based RL.
problem Efficient planning in continuous control settings with large prediction horizons.
method Combines CEM for exploration and gradient descent for exploitation.
result Achieves better performance with fewer samples and less computation time.
Study optimal paths in Zermelo's navigation problem using geometric equations.
problem Optimal control paths in Zermelo's navigation problem.
method Geometric and differential equations approach to obtain precise ODE system.
result Obtained precise equations for optimal trajectories.
Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-triv…
A framework clusters vehicle motion trajectories efficiently.
problem Costly manual annotation of vehicle motion data.
method Five-stage framework: align, embed, extract, embed, cluster.
result Framework achieves promising results on real-world dataset.
Reinforcement Learning optimizes low-thrust interplanetary trajectories under disturbances.
problem Designing robust interplanetary trajectories in the presence of disturbances.
method Reformulated as a Markov Decision Process, RL algorithm Proximal Policy Optimization trained on a deep neural network.
result Deep neural network provides robust nominal trajectory and guidance law.
DGFS improves sampling from complex densities by optimizing partial trajectories.
problem Sampling from intractable high-dimensional density functions.
method DGFS uses a flow function to break down the training process into short partial trajectory segments, leveraging intermediate learning signals.
result DGFS achieves more accurate estimates of the normalization constant.
Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradientcs.LG
Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy…
Myriad offers a testbed for integrating machine learning and trajectory optimization.
problem Real-world trajectory optimization challenges.
method JAX-based testbed with machine learning and trajectory optimization integration.
result End-to-end learning and planning with neural ODEs.
A large body of animation research focuses on optimization of movement control, either as action sequences or policy parameters. However, as closed-form expressions of the objective functions are often not available, our understanding of the optimization problems is limited. Building on recent work on analyzing neural …
Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel from the raw trajectory data? How can we infer such a mobility model from the single trajectory information? How can we further generalize the mobility inference to ac…
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past acti…
New method efficiently evaluates policies using trajectory data.
problem Statistically efficient policy evaluation with limited data.
method Trajectory-based approach for policy evaluation.
result Improved sample complexity for policy evaluation.
TRAKNN: Efficient Trajectory Aware Spatiotemporal kNN for Rare Meteorological Trajectory Detectionstat.ML
TRAKNN detects rare atmospheric trajectories efficiently.
problem Detecting rare atmospheric anomalies over long periods.
method Unsupervised, recurrence-based kNN algorithm.
result Rare trajectories correspond to physical anomalies.
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also Howcs.LG
New research suggests continual learning should focus on both optimization objective and optimization trajectory.
problem Even with perfect joint loss approximation, continual learning still suffers from forgetting when starting a new task.
method Proposes focusing on both optimization objective and optimization trajectory, combining replay-approximated joint objectives with gradient projection-based optimization routines.
result Combining replay-approximated joint objectives with gradient projection-based optimization routines did not show clear benefits in initial experiments.
Study shows bifurcation in optimal retirement planning.
problem Optimal consumption and retirement planning model.
method Cobb-Douglas utility, simple model with wealth bifurcation.
result Critical wealth level leads to a continuum of retirement trajectories.
Persistent Neuronscs.LG
Persistent neurons improve neural network optimization by leveraging previous solutions.
problem Improving neural network optimization under different initialization and data distributions.
method Persistent neurons use information from previous converged solutions to explore new landscapes and avoid local minima.
result Persistent neurons converge to more optimal solutions and improve model performance under various initializations.
New algorithm improves RL performance across different environments.
problem Improving reinforcement learning performance across various environments.
method Designing a fully model-free DRRL algorithm that learns from a single trajectory.
result Demonstrates superior robustness and sample efficiency compared to existing methods.
Measuring similarities between unlabeled time series trajectories is an important problem in domains as diverse as medicine, astronomy, finance, and computer vision. It is often unclear what is the appropriate metric to use because of the complex nature of noise in the trajectories (e.g. different sampling rates or out…
Two flat sub-Lorentzian problems on Martinet distribution differ in attainable set intersections.
problem Flat sub-Lorentzian structures on Martinet distribution.
method Analysis of attainable sets, optimal trajectories, sub-Lorentzian distances and spheres.
result The attainable set for the first problem intersects with the Martinet plane, while for the second it does not.
The paper studies sub and super-replication price bounds for contingent claims defined on general trajectory based market models. No prior probabilistic or topological assumptions are placed on the trajectory space, trading is assumed to take place at a finite number of occasions but not bounded in number nor necessari…