arXiv research

Study presents a low-cost local motion planner for vineyard navigation.

We introduce a variant of Farber's topological complexity, defined for smooth compact orientable Riemannian manifolds, which takes into account only motion planners with the lowest possible "average length" of the output paths. We prove that it never differs from topological complexity by more than $1$, thus showing th…

End-to-end learnable network for safer self-driving with interpretable intermediate representations.

We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models. It is efficient because (1) local models are estimated only when the planner requires them; (2) the planner focuses on the most relevant states to the current planni…

CoMPNetX uses neural networks to efficiently solve constrained motion planning problems.

This work improves motion planning for quadcopters by learning and reasoning about controller performance.

New research shows exponential lower bounds for planning in MDPs with linearly-realizable optimal action-value functions.

Financial planners helped preserve and increase household net financial assets during the Great Recession.

Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on different, yet similar problems. This setting is important in applications with rapidl…

Automated planning is one of the foundational areas of AI. Since no single planner can work well for all tasks and domains, portfolio-based techniques have become increasingly popular in recent years. In particular, deep learning emerges as a promising methodology for online planner selection. Owing to the recent devel…

We propose a reinforcement learning framework for discrete environments in which an agent makes both strategic and tactical decisions. The former manifests itself through the use of value function, while the latter is powered by a tree search planner. These tools complement each other. The planning module performs a lo…

Agent learns to navigate uncertain 3D maps using a hybrid planner.

Paper learns versatile balancing and recovery motions for humanoid robots.

XLVINs improve data efficiency in implicit planning by leveraging latent space.

Study optimal investment decisions for diverse risk-tolerant agents.

The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires flexible generative planning that can combine primitive abilities in novel combination…

The equation of a motion of curves in the projective plane is deduced. Local flows are defined in terms of polynomial differential functions. A family of local flows inducing the Kaup-Kupershmidt hierarchy is constructed. The integration of the congruence curves is discussed. Local motions defined by the traveling wave…

This paper proposes a representational model for image pairs such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The model couples the following two components: (1) the vector representations of loc…

Develops an equilibrium model for securities pricing in a mixed cooperative and non-cooperative market.

The paper optimizes pension policies with guarantees and sustainability constraints.

We derive the joint density of a Skew Brownian motion, its last visit to the origin, local and occupation times. The result is applied to option pricing in a two valued local volatility model and in a displaced diffusion model with constrained volatility.

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local a…

We present a robust multiple manifolds structure learning (RMMSL) scheme to robustly estimate data structures under the multiple low intrinsic dimensional manifolds assumption. In the local learning stage, RMMSL efficiently estimates local tangent space by weighted low-rank matrix factorization. In the global learning …

CEM-GD combines CEM and gradient descent for efficient model-based RL.

Collective motion is an intriguing phenomenon, especially considering that it arises from a set of simple rules governing local interactions between individuals. In theoretical models, these rules are normally \emph{assumed} to take a particular form, possibly constrained by heuristic arguments. We propose a new class …

We study a geometric flow where the motion of a set is driven by the mean curvature of its boundary and the normal derivative of its capacity potential. We establish local well-posedness and propose two possible weak formulations that exist after singularities.

Algorithm learns fair division from noisy feedback in uncertain markets.

We propose in this paper a constructive procedure that transforms locally, even at singular configurations, the kinematics of a car towing trailers into Kumpera-Ruiz normal form. This construction converts the nonholonomic motion planning problem into an algebraic problem (the resolution of a system of polynomial equat…

Improved model-based reinforcement learning for interactive dialogue tasks reduces sample needs and improves performance.

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have s…

We consider the task of learning to extract motion from videos. To this end, we show that the detection of spatial transformations can be viewed as the detection of synchrony between the image sequence and a sequence of features undergoing the motion we wish to detect. We show that learning about synchrony is possible …

It is common for CCTV operators to overlook inter- esting events taking place within the crowd due to large number of people in the crowded scene (i.e. marathon, rally). Thus, there is a dire need to automate the detection of salient crowd regions acquiring immediate attention for a more effective and proactive surveil…

This work proposes the use of Bayesian approximations of uncertainty from deep learning in a robot planner, showing that this produces more cautious actions in safety-critical scenarios. The case study investigated is motivated by a setup where an aerial robot acts as a "scout" for a ground robot. This is useful when t…

On the one hand, we prove that the Clifford torus in $\mathbb{C}^2$ is unstable for Lagrangian mean curvature flow under arbitrarily small Hamiltonian perturbations, even though it is Hamiltonian $F$-stable and locally area minimising under Hamiltonian variations. On the other hand, we show that the Clifford torus is r…

In this paper, we develop a theory of common decomposition for two correlated Brownian motions, in which, by using change of time method, the correlated Brownian motions are represented by a triplet of processes, $(X,Y,T)$, where $X$ and $Y$ are independent Brownian motions. We show the equivalent conditions for the tr…

We conduct cluster analysis on a class of locally asymptotically self-similar stochastic processes, which includes multifractional Brownian motion as a representative. When the true number of clusters is supposed to be known, a new covariance-based dissimilarity measure is introduced, from which we obtain the approxima…

Survey on manifold complexities and motion planning in robotics.

Modeling price dynamics in AMMs with fees using geometric Brownian motion.

TensorPlan algorithm finds δ-optimal policies with poly$(H,d)$ queries under linearly realizable state-value function.

We consider the motion by mean curvature of an $n$-dimensional graph over a time-dependent domain in $\mathbb{R}^n$, intersecting $\mathbb{R}^n$ at a constant angle. In the general case, we prove local existence for the corresponding quasilinear parabolic equation with a free boundary, and derive a continuation criteri…

Model analyzes optimal interbank networks during liquidity shocks, revealing core-periphery structures and co-investment requirements.

New approach improves black-box planning efficiency by discovering focused macros.

New algorithm learns FMDP structure while minimizing regret.

Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on othe…

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner would exploit model flaws, which can yield catastrophic failures. This paper focuse…

PBCS combines RL and motion planning for better exploration.

Developed a machine-checked Itô calculus for Brownian motion.

DDPD separates generation into planning and denoising for improved efficiency.