VTA learns hierarchical temporal structure for sequential data.
problem Learning interpretable temporal structure in sequential data.
method Hierarchical recurrent state space model with variational approach.
result VTA models 2D and 3D visual sequences with hierarchical structure.
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-…
Develops models for temporally abstract reasoning and attention.
problem Temporal abstraction and attention in reinforcement learning.
method Defines affordances for options and develops partial option models.
result Identifies trade-offs between estimation and approximation error.
New method learns temporal abstractions by defining interest functions.
problem Learning temporal abstractions with limited, variable durations.
method Introduced interest functions to define initiation sets, enabling gradient-based learning.
result Demonstrated effectiveness in discrete and continuous environments.
HO2 learns options from data efficiently, improving robot manipulation tasks.
problem Learning options from raw pixel inputs in 3D robot manipulation tasks.
method HO2 infers likely option choices and trains all policy components off-policy.
result HO2 outperforms existing methods on 3D robot manipulation tasks.
Enhanced LSTM model learns complex temporal dependencies.
problem Modeling long-term dependencies in sequential data.
method Gamma-LSTM with hierarchical memory units and gates.
result Gamma-LSTM outperforms regular and stacked LSTMs in sequence prediction.
Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn concepts and sub-skills that can be composed to solve longer tasks, i.e. hierarchical RL, w…
A method uses RL to learn abstractions for planning, improving robot navigation and manipulation tasks.
problem Planning requires suitable abstractions for states and transitions, which RL struggles with for temporally extended tasks.
method Goal-conditioned policies learned with RL are incorporated into planning, with a latent variable model representing valid states.
result Our method significantly outperforms prior work on image-based robot navigation and manipulation tasks.
We propose a recurrent extension of the Ladder networks whose structure is motivated by the inference required in hierarchical latent variable models. We demonstrate that the recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling. The arch…
The paper introduces a method to learn Markov state abstractions for reinforcement learning.
problem Learning Markov state representations in complex environments.
method The paper introduces a novel set of conditions and a training procedure combining inverse model estimation and temporal contrastive learning.
result The approach learns representations that capture the underlying structure of the domain and improve sample efficiency.
We introduce a method which enables a recurrent dynamics model to be temporally abstract. Our approach, which we call Adaptive Skip Intervals (ASI), is based on the observation that in many sequential prediction tasks, the exact time at which events occur is irrelevant to the underlying objective. Moreover, in many sit…
In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However…
Abstract Morse index theorem applied to various optimization problems.
problem Optimization problems with constraints in Hilbert spaces.
method Abstract Morse index theorem in Hilbert space.
result Precise changes in index and nullity when restricting to subspaces.
Mid-training improves RL by identifying compact action abstractions.
problem Unlocking full potential of RL with large language models.
method RA3 algorithm that optimizes sequential variational lower bound and discovers latent structures via RL.
result Improves performance by 8 points on HumanEval and 4 points on MBPP.
SG-NTF completes HDI tensors with spectral mapping and spatio-temporal gating.
problem High-dimensional and incomplete tensor completion.
method Spectra-Guided Neural Tucker Factorization (SG-NTF) with Spatio-Temporal Co-Gating (STCG).
result Maintains competitive completion accuracy with parameter efficiency.
Deep neural network learns discrete state abstractions for efficient planning.
problem Efficient sequential decision making in large state spaces.
method Information bottleneck method for learning approximate bisimulations using deep neural encoders and action-conditioned HMM.
result Trained method efficiently plans for unseen goals in multi-goal reinforcement learning.
DSARF models complex spatio-temporal data with deep switching auto-regressive factors.
problem Forecasting complex spatio-temporal data with recurring patterns.
method Deep switching auto-regressive factorization (DSARF) with stochastic variational inference.
result DSARF outperforms state-of-the-art methods in long- and short-term prediction accuracy.
Develops hierarchical reinforcement learning value function approximators.
problem Estimating long-term returns in reinforcement learning with multiple goals.
method Introduces hierarchical universal value function approximators (H-UVFAs) using the options framework.
result Demonstrates generalization and improved performance of H-UVFAs over UVFAs.
Agents compose pre-trained policies for complex tasks, improving zero-shot performance.
problem Challenges in long-horizon predictions and estimating visitation distributions induced by policy sequences.
method Learn predictive jumpy world models of multi-step dynamics, enhancing predictions with a consistency objective.
result Compositional planning with jumpy world models yields, on average, a 200% relative improvement over primitive actions on long-horizon tasks.
This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…
Efficient spatio-temporal Gaussian process inference method.
problem Scalable Gaussian process inference for multivariate, spatio-temporal data.
method Combines spatio-temporal filtering with natural gradient variational inference, resulting in a scalable non-conjugate GP method.
result Linear scaling with respect to time and logarithmic scaling with respect to time steps.
Neural attention (NA) has become a key component of sequence-to-sequence models that yield state-of-the-art performance in as hard tasks as abstractive document summarization (ADS) and video captioning (VC). NA mechanisms perform inference of context vectors; these constitute weighted sums of deterministic input sequen…
Generative model identifies temporal count data components with regime-dependent contributions.
problem Modeling temporal count data with regime-dependent dynamics.
method Generative framework combining regime-adaptive dynamics with Poisson log-normal emissions.
result Established identifiability of the model and revealed co-variation patterns and regime shifts.
This paper solves inverse reinforcement learning with options framework.
problem Reinforcement learning in complex environments with expert demonstrations.
method Gradient method for parametrized options, deducing Q-feature and reward feature spaces, optimal reward function selection.
result Recovered rewards provide effective solution to IRL problem and accelerate transfer learning.
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
problem Lack of provable guarantees for learning hierarchical structures in reinforcement learning.
method Analyzed HRL in meta-RL setting with tabular transition dynamics, providing diversity conditions and regret bounds.
result Sample-efficient recovery of natural hierarchical structure with provable guarantees.
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…
Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et al., 1999). However, only recently in (Bacon et al., 2017) was a policy gradient…
UTE improves reinforcement learning by measuring action uncertainty, enhancing policy learning efficiency.
problem Degrading performance of action repetition in reinforcement learning, especially with sub-optimal actions.
method UTE uses ensemble methods to measure uncertainty during action extension, allowing strategic exploration or certainty.
result UTE outperforms existing action repetition algorithms, significantly enhancing policy learning efficiency.
A new method for separating mixed signals in space and time.
problem Nonlinear and nonstationary spatio-temporal data challenges.
method Identifiable autoregressive variational autoencoder.
result The method outperforms existing techniques in blind source separation and spatio-temporal prediction.
This paper improves disentanglement in VAEs by progressively learning hierarchical representations.
problem Compromised disentanglement in VAEs due to high-level abstraction extraction.
method Progressive learning of independent hierarchical representations from high to low levels.
result Improved disentanglement demonstrated on two benchmark datasets using new metrics.
ST-MTM models complex time series by decomposing and masking seasonal and trend components.
problem Forecasting complex time series with intricate temporal variations.
method Seasonal-Trend Decomposition with Masking and Contrastive Learning.
result ST-MTM achieves superior forecasting performance compared to existing methods.
The paper learns robot skills from demonstrations without supervision.
problem Discovering robotic options from unlabelled demonstrations.
method Temporal variational inference for latent variable learning.
result The framework can learn options across multiple datasets.
DualVDT improves time-series forecasting with a novel dual reparametrized structure.
problem Time-series forecasting with improved performance and analytical rigor.
method Dual reparametrized variational mechanisms on VAE, latent score based generative model, reverse time stochastic differential equation, variational ancestral sampling, KL divergence reduction.
result Advanced performance in time-series forecasting with reduced KL divergence.
DMSTF models spatio-temporal data with deep Markov priors.
problem Analyzing nonlinear multimodal spatio-temporal dynamics.
method Deep Markov spatio-temporal factorization with stochastic variational inference.
result DMSTF outperforms other methods in predictive performance and clustering.
MLAT improves kNN performance in time series by learning metrics that align and capture temporal dependencies.
problem Improving kNN performance in time series by learning metrics that effectively handle variations and temporal dependencies.
method MLAT uses a sliding window to augment time series data and applies time-invariant metric learning to derive the most appropriate distance measure.
result MLAT outperforms other existing algorithms in various real-world data sets.
In the classical Lagrangian approach to conservation laws of gauge-natural field theories a suitable (vector) density is known to generate the so--called {\em conserved Noether currents}. It turns out that along any section of the relevant gauge--natural bundle this density is the divergence of a skew--symmetric (tenso…
Variational autoencoder models dynamic latent graphs for neural point processes.
problem Modeling event dynamics with changing trends over time.
method Sequential latent variable model with dynamic latent graphs.
result Higher accuracy in predicting inter-event times and event types.
NHC learns scalable algorithmic solutions from diverse tasks.
problem Neural networks struggle to learn algorithmic strategies.
method Memory-augmented network with abstraction mechanism and evolutionary training.
result Reliable learning of robust and scalable algorithmic solutions.
Paper models spatio-temporal extremes using conditional variational autoencoders.
problem Modeling co-occurrence of extreme weather events under changing climate conditions.
method Conditional Variational Autoencoder (cXVAE) with CNN integration.
result Accurately emulates spatial fields and recovers extremal dependence with low computational cost.
Generative Link Sequence Modeling predicts future links in evolving networks.
problem Predicting future links in networks with evolving structures.
method Sequence modeling framework with self-tokenization to capture temporal link formation patterns.
result GLSM achieves best performance on AUC metrics compared to existing methods.
Modeling complex systems with multi-resolution data and causal dependencies.
problem Accurate prediction of complex systems with varying causal dependencies and multi-resolution data.
method Score-based Variational Graphical Diffusion Model (Temporal-SVGDM) that constructs individual SDEs for each variable at its native resolution and couples them through a causal score mechanism.
result Improved prediction accuracy and causal understanding compared to existing methods, especially in temporal scenarios.
Neuro-symbolic agent learns systematic generalisation from formal instructions.
problem Achieving zero-shot generalisation of formally specified tasks.
method Combines deep reinforcement learning with temporal logic.
result Systematic learning emerges with convolutional layers and abstract operators.
We prove an extension of a celebrated equivariant bifurcation result of J. Smoller and A. Wasserman, in an abstract framework for geometric variational problems. With this purpose, we prove a slice theorem for continuous affine actions of a (finite-dimensional) Lie group on Banach manifolds. As an application, we discu…
Time-variant value function transfer method for RL.
problem Transfer learning with time-variant task distributions.
method Variational approach leveraging temporal structure.
result The proposed method outperforms time-invariant approach in experiments.
A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, …
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
The increased adoption of Electronic Health Records(EHRs) has brought changes to the way the patient care is carried out. The rich heterogeneous and temporal data space stored in EHRs can be leveraged by machine learning models to capture the underlying information and make clinically relevant predictions. This can be …
The variation of Hodge structure of a Calabi-Yau 3-fold induces a canonical Kähler metric on its Kuranishi moduli space, known as the Weil-Petersson metric. Similarly, special pseudo Kähler manifolds correspond to certain (abstract) variations of Hodge structure which generalize the above example. We give the classific…