DSE learns transferable skills across changing dynamics and goals.
problem Learning transferable skills across different reinforcement learning tasks.
method Variational inference for multi-task reinforcement learning with shared and task-specific latent spaces.
result Policies can generalize to unseen dynamics and goals conditions.
Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.
problem Sparse feedback learning with high-dimensional, hybrid, or contact-dependent dynamics.
method Introduces physics-informed inductive biases into goal-conditioned value learning.
result Contact-rich manipulation tasks degrade existing Pi-GCRL methods.
Adapts Floyd-Warshall algorithm for RL to improve multi-goal task learning.
problem Limited transfer of learned information in model-free RL for dynamic goal tasks.
method Adapts Floyd-Warshall algorithm for RL to learn goal-conditioned action-value functions.
result FWRL achieves higher reward strategies in multi-goal tasks with fewer samples.
Framework simplifies vision-based control and goal discovery.
problem Learning proportional control from visual data.
method Introduces NewtonianVAE for proportional control and goal discovery.
result Dramatic simplification and acceleration of vision-based controllers.
Automatically generates curricula for reinforcement learning agents.
problem Learning in dynamic, sparse reward environments.
method Setter-solver paradigm focusing on goal validity, feasibility, and coverage.
result Demonstrated success in 2D and 3D environments with varying goals.
Study maps interdependence of SDGs, finds complex, dynamic linkages.
problem Identify which SDGs promote progress and how quickly.
method Used a balanced panel of 114 countries from 2000 to 2024, applying two estimators to recover directed interaction network and measure dynamic linkages.
result 84 goal linkages survive false-discovery control, showing both synergies and trade-offs, with no single goal acting as a universal accelerator.
Paper proposes Imitative Models combining IL and planning for flexible goal achievement.
problem Difficult to direct IL to arbitrary goals and specify reward functions for goal-directed planning.
method Imitative Models are probabilistic predictive models that plan interpretable expert-like trajectories.
result Imitative Models outperform IL and planning approaches in a dynamic autonomous driving task.
Automatically learns dynamical distances for efficient reinforcement learning.
problem Difficult to specify reward functions for reinforcement learning.
method Uses dynamical distances to provide well-shaped reward functions.
result Can learn complex tasks efficiently with minimal supervision.
GOALS improves learning rate selection for dynamic MBSS in deep learning.
problem Challenges in selecting learning rates for dynamic MBSS in deep learning.
method Gradient-only approximation line search (GOALS) for dynamic MBSS loss functions.
result GOALS reduces model errors in multimodal cases.
A new trajectory representation method for AI problems.
problem Trajectory prediction and optimization in AI problems.
method Sub-goal trees, recursively partitioning trajectories into sub-segments.
result Sub-goal trees predict trajectories faster and more accurately.
Model for dynamic pricing across multiple RE groups to maximize revenue.
problem Maximizing revenue from multiple RE pricing groups.
method Mathematical model incorporating multiple pricing groups, revenue goals, and time value of money.
result Algorithm for constructing a pricing policy for multiple RE groups.
PCHID improves sample efficiency in reinforcement learning tasks.
problem Sparse rewards make learning policies difficult in reinforcement learning.
method Hindsight Inverse Dynamics with Hindsight Experience Replay and Policy Continuation.
result PCHID significantly improves sample efficiency and final performance on multi-goal tasks.
Paper proposes a method to make learned models focus on task-relevant information.
problem Mismatch between model objective and downstream task objective.
method Direct prediction towards task-relevant information, self-supervised.
result Model more effectively models relevant parts of the scene conditioned on the goal.
Eikonal-Constrained QRL improves goal-reaching in reinforcement learning.
problem Reward design and out-of-distribution generalization in reinforcement learning.
method Eikonal-Constrained Quasimetric Reinforcement Learning (Eik-QRL) using the Eikonal PDE.
result Eik-QRL achieves state-of-the-art performance in offline goal-conditioned navigation and manipulation tasks.
This work improves imitation learning and goal-conditioned RL by estimating value densities.
problem Effective solutions for imitation and goal-conditioned reinforcement learning require reliably reaching specified states or demonstrations.
method The approach uses recent advances in density estimation to learn value functions efficiently and without hindsight bias.
result The method achieves state-of-the-art demonstration sample-efficiency in imitation learning and is both efficient and bias-free in goal-conditioned reinforcement learning.
The goal of this paper, using lifting theory it is to produce almost paracomplex struc- tures on the tangent bundle of almost Lorentzian r-paracontact manifold endowed with almost Lorentzian r-paracontact structure. Finally, we discuss the effect over dynamics systems of the produced geometrical structures.
The paper proposes Tier Balancing for dynamic fairness in decision-making.
problem Achieving long-term fairness in decision-making processes.
method Causal modeling with DAGs to investigate dynamic fairness.
result Tier Balancing is a more natural approach to achieve long-term fairness, capturing latent causal factors.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
Recommender system improves with temporal representations.
problem Improving interpretability and performance in recommender systems.
method Incorporates temporal representations via recurrent point process in continuous time.
result Characterizes effects of perception, interest, and seasonal changes on reviews.
In this paper, we consider three problems related to survival, growth, and goal reaching maximization of an investment portfolio with proportional net cash flow. We solve the problems in a market constrained due to borrowing prohibition. To solve the problems, we first construct an auxiliary market and then apply the d…
New method predicts vehicle trajectories using map lane centers.
problem Accurate long-term vehicle trajectory prediction.
method Uses map lane centers to generate goal paths and predict trajectories.
result Model outperforms state-of-the-art approaches for 6-second horizon predictions.
We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task. While our goal could in principle be tackled by general reinforcement learning, our particular setting is constrained enough to allow more efficient algorithms. In this paper, we work under t…
The goal of this article is to describe the concepts of system dynamics and its applications to the simulation modeling of financial institutions daily activity. The hybrid method of the re-engineering of banking business processes based upon combination of system dynamics, queuing theory and tools of ordinary differen…
Reinforcement learning optimizes robot trajectories for unknown dynamics.
problem Optimizing robot trajectories for systems with unknown dynamics.
method Curriculum learning with reinforcement learning to generate smooth trajectories.
result Reinforcement learning agent outperforms PID controllers in trajectory tracking.
USFs capture dynamics for faster RL task transfer.
problem Applying knowledge from one task to another.
method Proposed Universal Successor Features (USFs) for RL.
result USFs accelerate training and transfer knowledge.
Develops a new learning framework for dynamic data.
problem Poor performance of existing strategies in dynamic data and goals.
method Prospective Learning framework and Prospective ERM algorithm.
result Prospective ERM converges to Bayes risk under certain assumptions.
Self-organized action hierarchy and compositionality learned by RNNs.
problem Improving RNN architectures for reinforcement learning.
method Multiple-timescale, stochastic RNN for RL.
result Network autonomously learns sub-goals and develops an action hierarchy.
We explain increases in clinical risk predictions over time.
problem Tackling the challenge of explaining dynamic risk increases in clinical settings.
method Developed methods to extend static attribution techniques to dynamic settings, addressing challenges specific to time-series data.
result Identified and addressed challenges specific to dynamic risk estimation, improving clinical alert explanations.
Method maps state space using landmarks for universal goal reaching.
problem Learning the Universal Value Function Approximator (UVFA) for long-range goals is challenging.
method Hierarchical modeling with a dynamic landmark-based map and a value network.
result The method enables agents to reach long-range goals at the early training stage.
New method uses autoregressive models for dynamic planning.
problem Planning in dynamic environments with moving obstacles and goals.
method Conditional autoregressive generative models in a discrete latent space.
result Method nearly matches true environment performance for planning.
Optimizes real estate prices with dynamic strategies.
problem Optimizing prices for limited real estate goods over time.
method Develops a mathematical model considering variable demand, time value, and growth of real estate value.
result Enhanced model for better revenue management in real estate.
Automated discovery of diverse self-organized patterns in complex systems.
problem Automated identification of interesting spatially localized patterns in self-organizing systems.
method Intrinsically motivated machine learning algorithms (POP-IMGEPs) combined with deep auto-encoders and CPPN primitives.
result Efficiency and effectiveness of the proposed method in discovering diverse patterns compared to baselines.
In this article we discuss some of the consequences of the mixed membership perspective on time series analysis. In its most abstract form, a mixed membership model aims to associate an individual entity with some set of attributes based on a collection of observed data. Although much of the literature on mixed members…
Paper improves RL efficiency by learning dynamic embeddings.
problem Improving sample efficiency in reinforcement learning.
method Proposes a forward prediction objective for state and action embeddings that capture dynamics.
result Action embeddings alone improve RL performance; combined state and action embeddings achieve efficient learning.
WayDCM predicts trajectories considering long-term goals, improving accuracy.
problem Predicting future trajectories of dynamic agents in complex environments.
method WayDCM combines DCM and NN to predict intermediate goals and trajectories, considering long-term goals.
result WayDCM outperforms previous methods on the Waymo Open dataset.
This article presents a theoretical model for a dynamic system based on sustainable development. Due to the relatively absence of theoretical studies and practical issues in the area of sustainable development, Romania aspires to the principles of sustainable development. Based on the concept as a process in which econ…
We describe a project, called the "Discretization in Geometry and Dynamics Gallery", or DGD Gallery for short, whose goal is to store geometric data and to make it publicly available. The DGD Gallery offers an online web service for the storage, sharing, and publication of digital research data.
Deep learning applies hierarchical layers of hidden variables to construct nonlinear high dimensional predictors. Our goal is to develop and train deep learning architectures for spatio-temporal modeling. Training a deep architecture is achieved by stochastic gradient descent (SGD) and drop-out (DO) for parameter regul…
Introduces HMC method for sampling Gibbs densities.
problem Sampling from Gibbs densities efficiently.
method Hamiltonian Monte Carlo (HMC) method based on Hamiltonian dynamics.
result Idealized HMC preserves the target distribution and converges under certain conditions.
Improves sparse reinforcement learning efficiency with OYMB.
problem Sparse rewards hinder reinforcement learning performance.
method Introduces OYMB, a sampler for HER to control minibatch makeup.
result HER combined with OYMB leads to faster real goal completion.
This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local…
Neural Shadow-Mapping uncovers causal links in dynamic systems.
problem Discovering causal structures in dynamic systems with mirage correlations.
method Neural network based method embedding high-dimensional data into a shadow representation for causal link estimation.
result Demonstrates performance in discovering causal links from video-representations of dynamic systems.
New framework embeds generalization in learning dynamics using large deviation theory.
problem Improving generalization and robustness in learning problems.
method Gradient methods from continuous-time perspective with Freidlin-Wentzell theory of large deviations.
result Asymptotic probability estimate for rare events in learning dynamics.
Survey explores interactions between four conformal dynamics branches.
problem Understanding complex dynamics through different mathematical concepts.
method Examples and general results with technical tools.
result Dynamical relations between Schwarz reflection parameter spaces and anti-rational maps/ reflection groups.
Transformers learn multi-step reasoning through gradient descent.
problem Understanding how transformers solve symbolic multi-step reasoning tasks.
method Theoretical analysis of gradient descent dynamics and multi-phase training.
result Trained one-layer transformers can solve both backward and forward reasoning tasks with generalization guarantees.
The paper develops methods to optimize personalized policies in complex causal pathways.
problem Optimizing policies in healthcare settings with entangled causal effects.
method Combining mediation analysis and dynamic treatment regime ideas for longitudinal data.
result Derived methods for learning high-quality policies from observational data.
Predicts multiple vehicle trajectories efficiently.
problem Predicting uncertain future motions of agents in dynamic scenes.
method Probabilistic framework learning latent variables for multi-step future modeling.
result State-of-the-art predictions on vehicle trajectory datasets.
It is well known that Lagrangian dynamical systems naturally arise in describing wave front dynamics in the limit of short waves (which is called pseudoclassical limit or limit of geometrical optics). Wave fronts are the surfaces of constant phase, their points move along lines which are called rays. In non-homogeneous…