A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Develops models for temporally abstract reasoning and attention.
HO2 learns options from data efficiently, improving robot manipulation tasks.
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. The options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, mu…
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-…
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…
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.
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…
Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand. In contrast, model-free reinforcement learning (RL) can acquire behaviors from l…
SG-NTF completes HDI tensors with spectral mapping and spatio-temporal gating.
Develops hierarchical reinforcement learning value function approximators.
Agents compose pre-trained policies for complex tasks, improving zero-shot performance.
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…
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
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.
In this paper, we present Gamma-LSTM, an enhanced long short term memory (LSTM) unit, to enable learning of hierarchical representations through multiple stages of temporal abstractions. Gamma memory, a hierarchical memory unit, forms the central memory of Gamma-LSTM with gates to regulate the information flow into var…
We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link formation patterns from the observed links with a sequence modeling framework and h…
Neuro-symbolic agent learns systematic generalisation from formal instructions.
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 …
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functio…
CAWs learn temporal network dynamics without node identities or edge attributes.
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…
Mid-training improves RL by identifying compact action abstractions.
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not poss…
GAT-AGNN learns stock trends using graph and attention mechanisms.
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit in generalizing to physical tasks in a combinatorial space the learner has not encountered before. We present object-centric perception, pred…
Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…
In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly…
Unified multilinear model for causal factor disentanglement.
Learning goal-directed behavior in environments with sparse feedback is a major challenge for reinforcement learning algorithms. The primary difficulty arises due to insufficient exploration, resulting in an agent being unable to learn robust value functions. Intrinsically motivated agents can explore new behavior for …
The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution of the performance. In this paper, we introduce micro-objective reinforcement le…
Detects changes in topic proportions over time in large text datasets.
Abstraction is a fundamental part when learning behavioral models of systems. Usually the process of abstraction is manually defined by domain experts. This paper presents a method to perform automatic abstraction for network protocols. In particular a weakly supervised clustering algorithm is used to build an abstract…
The paper aims to mathematically define and learn abstractions from data.
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interp…
Unified framework for causal models at different levels of abstraction.
Abstract MDPs enable strategic exploration and fast reward transfer in complex environments.
DSARF models complex spatio-temporal data with deep switching auto-regressive factors.
New approach to abstract neural network representations using renormalization group.
Study investigates how simple speech sounds can form abstract categories.
This study investigates the content of the published scientific literature in the fields of operations research and management science (OR/MS) since the early 1950s. Our study is based on 80,757 published journal abstracts from 37 of the leading OR/MS journals. We have developed a topic model, using Latent Dirichlet Al…
Abstract Neural Networks (ANNs) improve DNN verification efficiency.
A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artifici…
Algorithm finds latent structure in value functions for improved reinforcement learning.