The paper proposes a framework to reason about object dynamics for faster reinforcement learning.
problem Current reinforcement learning approaches lack prior knowledge about the environment, limiting efficiency.
method Integrates object dynamics and behavior into reinforcement learning to improve efficiency.
result Demonstrates the need for reasoning about object behavior and dynamics, leading to faster learning.
Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-s…
Abstract: Defines differential equations in tangent categories, providing conditions for completeness and new perspectives.
problem Defining and working with differential equations in abstract tangent categories.
method Introduces curve objects and dynamical systems, providing conditions for completeness and exploring exponential maps.
result Provides abstract conditions for dynamical systems to be complete and introduces differential exponential rig.
Introduces R-SSM for modeling multi-object dynamics with GNNs and normalizing flows.
problem Complex interactions and evolutions in multi-object systems are hard to model.
method Relational state-space model (R-SSM) using graph neural networks (GNNs) and normalizing flows.
result Empirically validated on synthetic and real datasets.
Bayesian methods improve tracking multiple objects through dynamic dependencies.
problem Tracking multiple objects with time-varying cardinality and unordered measurements.
method Employing Bayesian nonparametric models, specifically dependent Dirichlet and Pitman-Yor processes, for state estimation and Monte Carlo sampling for trajectory learning.
result The proposed methods outperform existing algorithms in estimating the time-varying number of objects and identifying object associations.
Modeling interacting objects with latent Gaussian process ODEs.
problem Time uncertainty-aware modeling of continuous-time dynamics of interacting objects.
method A new model using latent Gaussian process ordinary differential equations to infer independent dynamics and interactions.
result Our model improves long-term predictions and successfully encapsulates independent dynamics and interactions.
SCALOR learns scalable object representations for crowded scenes.
problem Scalability in scenes with many objects.
method Spatially-parallel attention and proposal-rejection mechanisms.
result SCALOR can handle up to a hundred objects in crowded scenes.
We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perception-prediction network (PPN). Consisting of a perception module that extracts representations of latent object properties and a prediction module that uses those extracted properties to simula…
New method optimizes multiple objectives using particle dynamics and gradient flow.
problem Optimizing multiple conflicting objectives in complex scenarios.
method Interacting particle method combining Langevin and birth-death dynamics with a dominance potential.
result Method effectively relocates dominated particles, improving Pareto optimality.
Soft geometric bias improves physical dynamics predictions.
problem Learning physical dynamics with exact group equivariance can degrade performance.
method Object-centric world models using geometric algebra neural networks.
result Soft geometric inductive bias leads to better physical fidelity predictions.
New architecture separates object state and behavior for better game dynamics.
problem Lack of systematicity in black-box models for dynamic environments.
method Factorizes declarative and procedural knowledge into object files and schemata.
result Improves generalization on environments with multiple object tokens.
This work learns visual representations for deformable objects using contrastive estimation.
problem Challenges in learning plannable visual representations for deformable objects.
method Jointly optimizes visual representation and dynamics models using contrastive estimation.
result Substantial improvements in performance over standard model-based learning techniques.
Paper proposes learning system dynamics from irregularly-sampled partial observations.
problem Capturing dynamics of multi-agent systems with irregular and partial observations.
method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.
result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.
In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic objects, and inpainting the static occluded background with plausible imagery. …
We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a probabilistic model that first generate noisy positions for each object through a separate linear state-space model, and then renders the positions of all objects in the same image through a high…
The central task in modeling complex dynamical systems is parameter estimation. This task involves numerous evaluations of a computationally expensive objective function. Surrogate-based optimization introduces a computationally efficient predictive model that approximates the value of the objective function. The stand…
Paper approximates solutions for complex decision processes with limited precision.
problem Approximating the set of all solutions for Multi-objective Markov Decision Processes.
method Limited precision approach based on White's multi-objective value-iteration dynamic programming algorithm.
result The number of calculated solutions is tractable and approximates the true Pareto front.
In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smooth dynamics, an opportunity is lost if an unsupervised objective function remains static during the training process. The absence of concre…
Top 8 robotic vision systems tackled lifelong object recognition challenges.
problem Lifelong learning in robotic vision for varied, dynamic environments.
method Design of a dataset with diverse conditions and rules for evaluation.
result Robotic vision systems improved over time with dynamic object appearances.
Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) …
LRSAO uses RL to dynamically select and unlearn auxiliary objectives for EA optimization.
problem Optimizing complex landscapes with evolutionary algorithms.
method Local Reinforcement Learning (RL) to dynamically select and unlearn auxiliary objectives.
result Improved optimization complexity from O(n2log(n)/ℓ) to Θ(n2/ℓ2+nlog(n)). Proposes a method to learn dynamic models for systems with variable number of objects.
problem Efficiently modeling systems with a variable number of objects.
method Uses graph neural networks and block-wise linear transition matrices to learn compositional Koopman operators.
result The method adapts to new environments and produces better control signals.
A new framework reduces inconsistencies in chaotic surrogate modeling.
problem Consistency issues between probabilistic objectives and dynamical system dynamics.
method KAFFEE (Kalman-Aware Framework For Ergodic Emulation), a differentiable extended Kalman filter.
result KAFFEE mitigates the dynamic-probabilistic consistency gap, improving reconstruction and predictive scores.
In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound f…
STOVE predicts convincing physical behavior in videos.
problem Learning models from videos with objects and interactions.
method Compositional state-space model combining image and dynamics models.
result Predicts videos with convincing physical behavior over hundreds of timesteps.
Study on neural networks with regularisation and its impact on training dynamics.
problem Understanding the dynamics of neural networks with regularization.
method Established explicit dynamics for neural networks with a regularizing term, linearizing around initialisation.
result The regularisation term modifies the standard NTK dynamics, leading to new insights into network training.
Bayesian nonparametric models improve multi-object tracking robustness and flexibility.
problem Challenges in multi-object tracking, including time-dependent cardinality, unordered measurements, and object labeling.
method Robust nonparametric methods for state prior modeling, incorporating dynamic object birth/death and survival.
result Proposed models estimate time-dependent object cardinality, provide object labeling, and identify associated measurements.
New framework solves dynamic bilevel optimization problems in reinforcement learning.
problem Dynamic objective functions in reinforcement learning and human feedback.
method Principled penalty-based methods for bilevel reinforcement learning.
result Demonstrated effectiveness of penalty-based algorithms in simulations.
Capsule networks improve with dynamic routing using Wasserstein objective.
problem Capsule networks struggle to consistently outperform traditional neural networks.
method Dynamic routing scheme using approximate Wasserstein objective to select capsules.
result Capsule network achieves over 1.2% improvement on CIFAR-10 with fewer parameters.
In this paper we construct some natural geometrical objects on the 1-jet space J^1(R,R^3), like a nonlinear connection, a Cartan linear connection (together with its d-torsions and d-curvatures), a jet "electromagnetic" d-field and its geometric "electromagnetic" Yang-Mills energy, starting from a given dynamical syste…
We introduce a topological object, called hairy Cantor set, which in many ways enjoys the universal features of objects like Jordan curve, Cantor set, Cantor bouquet, hairy Jordan curve, etc. We give an axiomatic characterisation of hairy Cantor sets, and prove that any two such objects in the plane are ambiently homeo…
The Lagrangian description of mechanical systems and the Legendre Transformation (considered as a passage from the Lagrangian to the Hamiltonian formulation of the dynamics) for point-like objects, for which the infinitesimal configuration space is TM, is based on the existence of canonical symplectic isomorphisms of d…
Designs a framework to transfer causal models between similar environments.
problem Transferability of causal models between different but similar environments.
method Object-oriented representations and continuous optimization for structure learning.
result Demonstrates advantages in gridworld settings using reinforcement learning.
This work discovers latent field effects governing interacting dynamical systems.
problem Discovering field effects governing interacting dynamical systems.
method Proposes neural fields to learn latent force fields from observed dynamics, disentangling local object interactions and global field effects.
result Accurately discovers latent field effects in various dynamical systems.
This paper improves forecast stability without sacrificing accuracy using dynamic loss weighting.
problem Rolling origin forecast instability in time series forecasting.
method Dynamic loss weighting algorithms applied to the N-BEATS model.
result Dynamic loss weighting can further improve forecast stability without compromising accuracy.
New online algorithms tackle dynamic decision-focused learning.
problem Dynamic decision-focused learning in evolving environments.
method Regularization and perturbation techniques for non-convex optimization.
result First provable guarantees for online decision-focused learning.
Paper identifies objective mismatch in MBRL, affecting control task performance.
problem Objective mismatch in MBRL framework affects control task performance.
method Proposes re-weighting dynamics model training to mitigate mismatch.
result Likelihood of one-step ahead predictions is not always correlated with control performance.
Games generalize the single-objective optimization paradigm by introducing different objective functions for different players. Differentiable games often proceed by simultaneous or alternating gradient updates. In machine learning, games are gaining new importance through formulations like generative adversarial netwo…
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework for unsupervised learning of seq…
We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running …
Neural model predicts object states and physical parameters from visual observations.
problem Computational models struggle with physical reasoning and adapting to new environments.
method Visual prior predicts particle-based system from visual observations; inference module refines estimates subject to dynamics constraints.
result Model can infer physical properties within a few observations and adapt to unseen scenarios.
New neural network designs learn contact dynamics efficiently.
problem Learning contact dynamics in robotics from noisy data.
method Physically structured neural networks.
result Data-efficient learning of discontinuous contact events.
A novel tracking algorithm models dynamic objects as ellipsoids with time-varying orientation.
problem Tracking dynamic objects with time-varying orientation.
method Random matrix framework with variational Bayes for non-linear inference.
result The method outperforms state-of-the-art methods in accuracy and robustness.
This paper examines challenges and solutions for solving variational inequalities.
problem Stability issues in solving variational inequalities, especially in multi-objective scenarios.
method Continuous-time analysis to understand and improve stability of algorithms.
result Understanding continuous-time dynamics can help in designing more stable algorithms for variational inequalities.
Proposes local coordinate frames for improving model performance in complex dynamical systems.
problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.
Paper uses RL for dynamic swaption hedging, outperforming traditional methods.
problem Dynamic hedging of swaptions using reinforcement learning.
method Design agents with three objective functions to adapt hedging strategies dynamically.
result Deep hedging strategies using two swaps outperform traditional methods, even with model misspecification.
Classical knot theory deals with {\em diagrams} and {\em invariants}. By means of horizontal {\em trisecants}, we construct a new theory of classical braids with invariants valued in {\em pictures}. These pictures are closely related to diagrams of the initial object. The main tool is the notion of {\em free k-braid …
SPARTAN learns sparse interaction graphs between objects in scenes.
problem Capturing structured interactions between entities in complex settings remains challenging.
method SPARTAN is a Transformer-based world model that learns sparse, context-dependent interaction graphs through sparsity regularization on attention patterns.
result SPARTAN achieves significantly improved few-shot adaptation to dynamics changes and robustness against distractors.