arXiv research

Deep network predicts action sequences for complex tasks from a scene image.

Future autonomous systems need reliable world models and complex action sequences.

Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex action sequences. In this work, we address the problem of learning an agent's action…

In this paper we present the construction of explicit quasi-isomorphisms that compute the cyclic homology and periodic cyclic homology of crossed-product algebras associated with (discrete) group actions. In the first part we deal with algebraic crossed-products associated with group actions on unital algebras over any…

The curve graph and related graphs are hyperbolic and have quasi-tree fibers.

Develops a spectral sequence for Lie group actions on manifolds.

This work is motivated by two problems: 1) The approach of manifolds and spaces by triangulations. 2) The complexity growth in sequences of polyhedra. Considering both problems as related, new criteria and methods for approximating smooth manifolds are deduced. When the sequences of polyhedra are obtained by the action…

We show that the Frölicher spectral sequence of a complex parallelizable solvmanifold is degenerate at $E_{2}$-term. For a semi-direct product $G=\C^{n}\ltimes_φN$ of Lie-groups with lattice $Γ=Γ^{\prime}\ltimes Γ^{\prime\prime}$ such that $N$ is a nilpotent Lie-group with a left-invariant complex structure and $φ$ is …

Study group actions in metric spaces, proving convergence of lens spaces.

Through the theory of Lie bi-algebroids and generalized complex structures, one could define a cohomology theory naturally associated to a holomorphic Poisson structure. It is known that it is the hypercohomology of a bi-complex such that one of the two operators is the classical $\overline{\partial}$-operator. Another…

Study of Torelli group action on complex of cycles yields infinite generation result.

Study on spectral sequence for abelian Lie group actions, with bounds and applications.

We introduce and study a new spectral sequence associated with a Poisson group action on a Poisson manifold and an equivariant momentum mapping. This spectral sequence is a Poisson analog of the Leray spectral sequence of a fibration. The spectral sequence converges to the Poisson cohomology of the manifold and has the…

The paper examines the topology of quaternionic toric actions on manifolds.

Hybridizes CEM and gradient descent for efficient model-predictive control.

One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on human…

Study braid group actions on exceptional sequences using branched coverings.

Homological stability for sequences of groups is often proved by studying the spectral sequence associated to the action of a typical group in the sequence on a highly-connected simplicial complex whose stabilizers are related to previous groups in the sequence. In the case of mapping class groups of manifolds, suitabl…

Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement learning agent only has access to the state sequences of an expert, while the expe…

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop prediction methods that perform well against complex benchmarks. In this paper, we…

A method to generate long-range human actions by leveraging graph convolutional networks and self-attention.

Improved action recognition in live videos with hybrid FR-DL method.

A new method for disentangling action sequences improves model stability.

AR CI framework handles complex confounders and sequential actions.

We compute the equivariant complex K-theory ring of a cohomogeneity-one action of a compact Lie group at the level of generators and relations and derive a characterization of K-theoretic equivariant formality for these actions. Less explicit expressions survive for a range of equivariant cohomology theories including …

Enhances sequence memory capacity in neural networks.

Consider a manifold endowed with the action of a Lie group. We study the relation between the cohomology of the Cartan complex and the equivariant cohomology by using the equivariant De Rham complex developed by Getzler, and we show that the cohomology of the Cartan complex lies on the 0-th row of the second page of a …

Study of orbifold mapping class groups via arc and curve actions.

New algorithm tackles nonstationary linear bandits with latent dynamics.

Improved GFlowNets learn more efficiently with trajectory balance.

SocialInteractionGAN generates realistic human interactions from low-dimensional data.

New Smith-Gysin sequence for non-semi-free actions without semi-free condition.

A cohomology theory associated to a holomorphic Poisson structure is the hypercohomology of a bi-complex where one of the two operators is the classical $\overline\partial$-operator, while the other operator is the adjoint action of the Poisson bivector with respect to the Schouten-Nijenhuis bracket. The first page of …

We describe the basic cohomology ring of the canonical holomorphic foliation on a moment-angle manifold, LVMB-manifold or any complex manifold with a maximal holomorphic torus action. Namely, we show that the basic cohomology has a description similar to the cohomology ring of a complete simplicial toric variety due to…

Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR) model, termed the clustering-aware structure-constrained low-rank representation (CS…

Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape explor…

Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with …

It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequ…

Improves text-to-speech speed by interleaving character reading and audio synthesis.

A new homomorphism connects group actions on circles to Euler classes.

Agents compose pre-trained policies for complex tasks, improving zero-shot performance.

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…

Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservab…

A 2-manifold's group structure is deduced from orbit configuration spaces.

We construct an infinite tower of covering spaces over the configuration space of $n-1$ distinct non-zero points in the complex plane. This results in an action of the braid group $\mathbb{B}_n$ on the set of $n$-adic integers $\mathbb{Z}_n$ for all natural numbers $n\geq 2$. We study some of the properties of these ac…

Computer simulations have become a popular tool of assessing complex skills such as problem-solving skills. Log files of computer-based items record the entire human-computer interactive processes for each respondent. The response processes are very diverse, noisy, and of nonstandard formats. Few generic methods have b…

Khovanov homology for pro-tangles and spectral sequences

We construct a graph complex calculating the integral ho- mology of the bordered mapping class groups. We compute the ho- mology of the bordered mapping class groups of various surfaces. Using the circle action on this graph complex, we build a double complex and a spectral sequence converging to the homology of the un…