Search Results for author: Manuela Veloso

Found 37 papers, 4 papers with code

Advising Agent for Service-Providing Live-Chat Operators

no code implementations9 May 2021 Aviram Aviv, Yaniv Oshrat, Samuel A. Assefa, Tobi Mustapha, Daniel Borrajo, Manuela Veloso, Sarit Kraus

Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce.

Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods

no code implementations25 Feb 2021 Nicholay Topin, Stephanie Milani, Fei Fang, Manuela Veloso

Because of this decision tree equivalence, any function approximator can be used during training, including a neural network, while yielding a decision tree policy for the base MDP.

Deep Video Prediction for Time Series Forecasting

no code implementations24 Feb 2021 Zhen Zeng, Tucker Balch, Manuela Veloso

In this paper, we propose to approach economic time series forecasting of multiple financial assets in a novel way via video prediction.

Decision Making Time Series +2

Visual Forecasting of Time Series with Image-to-Image Regression

no code implementations18 Nov 2020 Naftali Cohen, Srijan Sood, Zhen Zeng, Tucker Balch, Manuela Veloso

In this work, we take a novel approach by leveraging advances in deep learning to extend the field of time series forecasting to a visual setting.

Quantization Time Series +1

Simulating and classifying behavior in adversarial environments based on action-state traces: an application to money laundering

no code implementations3 Nov 2020 Daniel Borrajo, Manuela Veloso, Sameena Shah

One of the key characteristics of these applications is the wide range of strategies that an adversary may choose as they adapt their strategy dynamically to sustain benefits and evade authorities.

Robust Document Representations using Latent Topics and Metadata

no code implementations23 Oct 2020 Natraj Raman, Armineh Nourbakhsh, Sameena Shah, Manuela Veloso

Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems.

Document Classification Language Modelling

SURF: Improving classifiers in production by learning from busy and noisy end users

no code implementations12 Oct 2020 Joshua Lockhart, Samuel Assefa, Ayham Alajdad, Andrew Alexander, Tucker Balch, Manuela Veloso

We show that conventional crowdsourcing algorithms struggle in this user feedback setting, and present a new algorithm, SURF, that can cope with this non-response ambiguity.

Paying down metadata debt: learning the representation of concepts using topic models

no code implementations9 Oct 2020 Jiahao Chen, Manuela Veloso

We introduce a data management problem called metadata debt, to identify the mapping between data concepts and their logical representations.

Topic Models

DocuBot : Generating financial reports using natural language interactions

no code implementations2 Oct 2020 Vineeth Ravi, Selim Amrouni, Andrea Stefanucci, Armineh Nourbakhsh, Prashant Reddy, Manuela Veloso

Digital reports are often created based on tedious manual analysis as well as visualization of the underlying trends and characteristics of data.

Calibration of Shared Equilibria in General Sum Partially Observable Markov Games

no code implementations NeurIPS 2020 Nelson Vadori, Sumitra Ganesh, Prashant Reddy, Manuela Veloso

Training multi-agent systems (MAS) to achieve realistic equilibria gives us a useful tool to understand and model real-world systems.

Risk-Sensitive Reinforcement Learning: a Martingale Approach to Reward Uncertainty

no code implementations23 Jun 2020 Nelson Vadori, Sumitra Ganesh, Prashant Reddy, Manuela Veloso

We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems.

Decision Making Portfolio Optimization

Guaranteeing Reproducibility in Deep Learning Competitions

no code implementations12 May 2020 Brandon Houghton, Stephanie Milani, Nicholay Topin, William Guss, Katja Hofmann, Diego Perez-Liebana, Manuela Veloso, Ruslan Salakhutdinov

To encourage the development of methods with reproducible and robust training behavior, we propose a challenge paradigm where competitors are evaluated directly on the performance of their learning procedures rather than pre-trained agents.

Some people aren't worth listening to: periodically retraining classifiers with feedback from a team of end users

no code implementations27 Apr 2020 Joshua Lockhart, Samuel Assefa, Tucker Balch, Manuela Veloso

Document classification is ubiquitous in a business setting, but often the end users of a classifier are engaged in an ongoing feedback-retrain loop with the team that maintain it.

Document Classification

Bayesian Consensus: Consensus Estimates from Miscalibrated Instruments under Heteroscedastic Noise

no code implementations14 Apr 2020 Chirag Nagpal, Robert E. Tillman, Prashant Reddy, Manuela Veloso

We consider the problem of aggregating predictions or measurements from a set of human forecasters, models, sensors or other instruments which may be subject to bias or miscalibration and random heteroscedastic noise.

Bayesian Inference

Heuristics for Link Prediction in Multiplex Networks

no code implementations9 Apr 2020 Robert E. Tillman, Vamsi K. Potluru, Jiahao Chen, Prashant Reddy, Manuela Veloso

Through experiments with simulated and real world scientific collaboration, transportation and global trade networks, we demonstrate that the proposed heuristics show increased performance with the richness of connection type correlation structure and significantly outperform their baseline heuristics for ordinary networks with a single connection type.

Link Prediction

Get Real: Realism Metrics for Robust Limit Order Book Market Simulations

no code implementations10 Dec 2019 Svitlana Vyetrenko, David Byrd, Nick Petosa, Mahmoud Mahfouz, Danial Dervovic, Manuela Veloso, Tucker Hybinette Balch

Machine learning (especially reinforcement learning) methods for trading are increasingly reliant on simulation for agent training and testing.

Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning

no code implementations28 Nov 2019 Rui Silva, Miguel Vasco, Francisco S. Melo, Ana Paiva, Manuela Veloso

In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities.

OpenAI Gym

On the Importance of Opponent Modeling in Auction Markets

no code implementations28 Nov 2019 Mahmoud Mahfouz, Angelos Filos, Cyrine Chtourou, Joshua Lockhart, Samuel Assefa, Manuela Veloso, Danilo Mandic, Tucker Balch

The dynamics of financial markets are driven by the interactions between participants, as well as the trading mechanisms and regulatory frameworks that govern these interactions.

Reinforcement Learning for Market Making in a Multi-agent Dealer Market

1 code implementation14 Nov 2019 Sumitra Ganesh, Nelson Vadori, Mengda Xu, Hua Zheng, Prashant Reddy, Manuela Veloso

Market makers play an important role in providing liquidity to markets by continuously quoting prices at which they are willing to buy and sell, and managing inventory risk.

Leveraging Multimodal Haptic Sensory Data for Robust Cutting

no code implementations27 Sep 2019 Kevin Zhang, Mohit Sharma, Manuela Veloso, Oliver Kroemer

In this paper, we propose using vibrations and force-torque feedback from the interactions to adapt the slicing motions and monitor for contact events.

MineRL: A Large-Scale Dataset of Minecraft Demonstrations

no code implementations29 Jul 2019 William H. Guss, Brandon Houghton, Nicholay Topin, Phillip Wang, Cayden Codel, Manuela Veloso, Ruslan Salakhutdinov

Therefore, we introduce a comprehensive, large-scale, simulator-paired dataset of human demonstrations: MineRL.

Minecraft

Trading via Image Classification

no code implementations23 Jul 2019 Naftali Cohen, Tucker Balch, Manuela Veloso

The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms all relying, primary, on aspects of time-series analysis.

Classification General Classification +4

The Effect of Visual Design in Image Classification

no code implementations22 Jul 2019 Naftali Cohen, Tucker Balch, Manuela Veloso

In this study, we examine whether binary decisions are better to be decided based on the numeric or the visual representation of the same data.

Classification Feature Engineering +2

Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy

no code implementations2 Jul 2019 Aaron M. Roth, Nicholay Topin, Pooyan Jamshidi, Manuela Veloso

There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI."

Generation of Policy-Level Explanations for Reinforcement Learning

no code implementations28 May 2019 Nicholay Topin, Manuela Veloso

Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use.

The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors

1 code implementation22 Apr 2019 William H. Guss, Cayden Codel, Katja Hofmann, Brandon Houghton, Noboru Kuno, Stephanie Milani, Sharada Mohanty, Diego Perez Liebana, Ruslan Salakhutdinov, Nicholay Topin, Manuela Veloso, Phillip Wang

To that end, we introduce: (1) the Minecraft ObtainDiamond task, a sequential decision making environment requiring long-term planning, hierarchical control, and efficient exploration methods; and (2) the MineRL-v0 dataset, a large-scale collection of over 60 million state-action pairs of human demonstrations that can be resimulated into embodied trajectories with arbitrary modifications to game state and visuals.

Decision Making Efficient Exploration +1

The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting

1 code implementation10 Jun 2018 Aaron M. Roth, Umang Bhatt, Tamara Amin, Afsaneh Doryab, Fei Fang, Manuela Veloso

In this pilot study, we investigate (1) in what way a robot can express a certain mood to influence a human's decision making behavioral model; (2) how and to what extent the human will be influenced in a game theoretic setting.

Decision Making Human robot interaction

Understanding Convolutional Networks with APPLE : Automatic Patch Pattern Labeling for Explanation

no code implementations11 Feb 2018 Sandeep Konam, Ian Quah, Stephanie Rosenthal, Manuela Veloso

With the success of deep learning, recent efforts have been focused on analyzing how learned networks make their classifications.

Classification General Classification

What Can This Robot Do? Learning from Appearance and Experiments

no code implementations15 Dec 2017 Ashwin Khadke, Manuela Veloso

We present an approach to make the learner build a model of the subject at a task based on the latter's appearance and refine it by experimentation.

UAV and Service Robot Coordination for Indoor Object Search Tasks

no code implementations26 Sep 2017 Sandeep Konam, Stephanie Rosenthal, Manuela Veloso

In this paper, we propose the concept of coordination between CoBot and the Parrot ARDrone 2. 0 to perform service-based object search tasks, in which CoBot localizes and navigates to the general search areas carrying the ARDrone and the ARDrone searches locally for objects.

Interactive Policy Learning through Confidence-Based Autonomy

no code implementations15 Jan 2014 Sonia Chernova, Manuela Veloso

We present Confidence-Based Autonomy (CBA), an interactive algorithm for policy learning from demonstration.

Trajectory-Based Short-Sighted Probabilistic Planning

no code implementations NeurIPS 2012 Felipe Trevizan, Manuela Veloso

In order to compute a solution for a probabilistic planning problem, planners need to manage the uncertainty associated with the different paths from the initial state to a goal state.

Cannot find the paper you are looking for? You can Submit a new open access paper.