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.
Study combines chit-chat and goal-oriented dialogue in fantasy games.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
A new method reduces both input and output dimensions for better goal-oriented analysis.
DGC clusters data with side-information for better prediction.
GOLOMB improves dialogue state tracking for unseen services.
GO-CBED optimizes experiments for specific causal queries, improving efficiency.
End-to-end dialogue model learns from joint embeddings and user intent.
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…
A new method for experimental design focuses on predicting downstream quantities of interest.
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning pr…
Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new approach called Policy Continuation with Hindsight Inverse Dynamics (PCHID). Th…
A Boolean algebra formalizes task composition for reinforcement learning.
A new GP interpolation method for better predictive distributions in ranges of interest.
The study optimizes sampling in complex systems with probabilistic response distributions.
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extension…
Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructi…
Deep learning improves conversational recommender systems.
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten ta…
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace singl…
ClovaCall introduces a new Korean call speech corpus for contact centers.
Unified LLM-agent with RL improves financial trading performance.
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficien…
Unmanned Aerial Vehicles (UAVs), autonomously-guided aircraft, are widely used for tasks involving surveillance and reconnaissance. A version of the pursuit-evasion problems centered around UAVs and its variants has been extensively studied in recent years due to numerous breakthroughs in AI. We present an approach to …
Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.
FastSGT improves accuracy in BERT-based DST for SGD datasets.
Method analyzes hyperparameters using HSIC for better neural network performance.
GO-OED maximizes predictive information gain on nonlinear QoIs.
This paper calibrates Gaussian process predictive distributions for Bayesian optimization to improve sampling decisions.
Paper tackles offline SSP with value iteration for policy evaluation and learning.
Question-answering systems and voice assistants are becoming major part of client service departments of many organizations, helping them to reduce the labor costs of staff. In many such systems, there is always natural language understanding module that solves intent classification task. This task is complicated becau…
Emotions are intimately tied to motivation and the adaptation of behavior, and many animal species show evidence of emotions in their behavior. Therefore, emotions must be related to powerful mechanisms that aid survival, and, emotions must be evolutionary continuous phenomena. How and why did emotions evolve in nature…
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation …
vsOED optimizes experiment design with reinforcement learning for Bayesian models.
Active learning (AL) concerns itself with learning a model from as few labelled data as possible through actively and iteratively querying an oracle with selected unlabelled samples. In this paper, we focus on analyzing a popular type of AL in which the utility of a sample is measured by a specified goal achieved by th…
Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly…
This paper accelerates inverse solutions for PDEs using ML and ROMs.
This paper develops a framework for efficient decision-making under time pressure.
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will …
Survey examines agentic AI in finance, highlighting its autonomy and challenges.
Oja's rule improves neural network training without engineered tricks.
CRPS improves GP-based sequential design for chemical space.
Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (SSP) formulation, where an agent has to achieve a goal state while minimizing the cumulative cost. Despite the popularity of this setting, t…
Proposes a real-time anomaly detection system using IRL.
Paper tackles efficient navigation in constrained environments using supervised and reinforcement learning.
We speed up Gaussian process cross-validation calculations and improve model diagnostics.
We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal…
This paper reviews dMTL and methods for selecting auxiliary tasks.