arXiv subjects

Manuela Veloso

Publications and source records attributed to Manuela Veloso.

At least 127 records · Page 7Linked to original sources

arXiv2020

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

We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards, which has the advantage of being conceptually more meaningful in some cases. To this end, we present a new decomposition of the randomness contained in the cumulative reward based on the Doob decomposition of a stochastic process, and introduce a new conceptual tool - the \textit{chaotic variation} - which can rigorously be interpreted as the risk measure of the martingale component associated to the cumulative reward process. We innovate on the reinforcement learning side by incorporating this new risk-sensitive approach into model-free algorithms, both policy gradient and value function based, and illustrate its relevance on grid world and portfolio optimization problems.

cs.LG↗

arXiv2020

Guaranteeing Reproducibility in Deep Learning Competitions

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. Since competition organizers re-train proposed methods in a controlled setting they can guarantee reproducibility, and -- by retraining submissions using a held-out test set -- help ensure generalization past the environments on which they were trained.

cs.LG↗

arXiv2020

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

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. We consider this feedback-retrain loop from a multi-agent point of view, considering the end users as autonomous agents that provide feedback on the labelled data provided by the classifier. This allows us to examine the effect on the classifier's performance of unreliable end users who provide incorrect feedback. We demonstrate a classifier that can learn which users tend to be unreliable, filtering their feedback out of the loop, thus improving performance in subsequent iterations.

cs.LG↗

arXiv2020

Heuristics for Link Prediction in Multiplex Networks

Link prediction, or the inference of future or missing connections between entities, is a well-studied problem in network analysis. A multitude of heuristics exist for link prediction in ordinary networks with a single type of connection. However, link prediction in multiplex networks, or networks with multiple types of connections, is not a well understood problem. We propose a novel general framework and three families of heuristics for multiplex network link prediction that are simple, interpretable, and take advantage of the rich connection type correlation structure that exists in many real world networks. We further derive a theoretical threshold for determining when to use a different connection type based on the number of links that overlap with an Erdos-Renyi random graph. 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.

cs.LG↗

arXiv2019

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

Machine learning (especially reinforcement learning) methods for trading are increasingly reliant on simulation for agent training and testing. Furthermore, simulation is important for validation of hand-coded trading strategies and for testing hypotheses about market structure. A challenge, however, concerns the robustness of policies validated in simulation because the simulations lack fidelity. In fact, researchers have shown that many market simulation approaches fail to reproduce statistics and stylized facts seen in real markets. As a step towards addressing this we surveyed the literature to collect a set of reference metrics and applied them to real market data and simulation output. Our paper provides a comprehensive catalog of these metrics including mathematical formulations where appropriate. Our results show that there are still significant discrepancies between simulated markets and real ones. However, this work serves as a benchmark against which we can measure future improvement.

q-fin.TR↗

arXiv2019

On the Importance of Opponent Modeling in Auction Markets

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. Decision-makers would rather not ignore the impact of other participants on these dynamics and should employ tools and models that take this into account. To this end, we demonstrate the efficacy of applying opponent-modeling in a number of simulated market settings. While our simulations are simplified representations of actual market dynamics, they provide an idealized "playground" in which our techniques can be demonstrated and tested. We present this work with the aim that our techniques could be refined and, with some effort, scaled up to the full complexity of real-world market scenarios. We hope that the results presented encourage practitioners to adopt opponent-modeling methods and apply them online systems, in order to enable not only reactive but also proactive decisions to be made.

q-fin.CP↗

arXiv2019

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

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. We propose a three-stage architecture that allows a reinforcement learning agent trained over a given sensory modality, to execute its task on a different sensory modality-for example, learning a visual policy over image inputs, and then execute such policy when only sound inputs are available. We show that the generalized policies achieve better out-of-the-box performance when compared to different baselines. Moreover, we show this holds in different OpenAI gym and video game environments, even when using different multimodal generative models and reinforcement learning algorithms.

cs.AI↗

arXiv2019

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

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. In this paper, we build a multi-agent simulation of a dealer market and demonstrate that it can be used to understand the behavior of a reinforcement learning (RL) based market maker agent. We use the simulator to train an RL-based market maker agent with different competitive scenarios, reward formulations and market price trends (drifts). We show that the reinforcement learning agent is able to learn about its competitor's pricing policy; it also learns to manage inventory by smartly selecting asymmetric prices on the buy and sell sides (skewing), and maintaining a positive (or negative) inventory depending on whether the market price drift is positive (or negative). Finally, we propose and test reward formulations for creating risk averse RL-based market maker agents.

q-fin.TR↗

arXiv2019

A Robot's Expressive Language Affects Human Strategy and Perceptions in a Competitive Game

As robots are increasingly endowed with social and communicative capabilities, they will interact with humans in more settings, both collaborative and competitive. We explore human-robot relationships in the context of a competitive Stackelberg Security Game. We vary humanoid robot expressive language (in the form of "encouraging" or "discouraging" verbal commentary) and measure the impact on participants' rationality, strategy prioritization, mood, and perceptions of the robot. We learn that a robot opponent that makes discouraging comments causes a human to play a game less rationally and to perceive the robot more negatively. We also contribute a simple open source Natural Language Processing framework for generating expressive sentences, which was used to generate the speech of our autonomous social robot.

cs.HC↗

arXiv2019

Leveraging Multimodal Haptic Sensory Data for Robust Cutting

Cutting is a common form of manipulation when working with divisible objects such as food, rope, or clay. Cooking in particular relies heavily on cutting to divide food items into desired shapes. However, cutting food is a challenging task due to the wide range of material properties exhibited by food items. Due to this variability, the same cutting motions cannot be used for all food items. Sensations from contact events, e.g., when placing the knife on the food item, will also vary depending on the material properties, and the robot will need to adapt accordingly. In this paper, we propose using vibrations and force-torque feedback from the interactions to adapt the slicing motions and monitor for contact events. The robot learns neural networks for performing each of these tasks and generalizing across different material properties. By adapting and monitoring the skill executions, the robot is able to reliably cut through more than 20 different types of food items and even detect whether certain food items are fresh or old.

cs.RO↗

arXiv2019

The Effect of Visual Design in Image Classification

Financial companies continuously analyze the state of the markets to rethink and adjust their investment strategies. While the analysis is done on the digital form of data, decisions are often made based on graphical representations in white papers or presentation slides. 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. Using two data sets, a matrix of numerical data with spatial dependencies and financial data describing the state of the S&P index, we compare the results of supervised classification based on the original numerical representation and the visual transformation of the same data. We show that, for these data sets, the visual transformation results in higher predictability skill compared to the original form of the data. We suggest thinking of the visual representation of numeric data, effectively, as a combination of dimensional reduction and feature engineering techniques. In particular, if the visual layout encapsulates the full complexity of the data. In this view, thoughtful visual design can guard against overfitting, or introduce new features -- all of which benefit the learning process, and effectively lead to better recognition of meaningful patterns.

cs.CV↗

arXiv2019

MineRL: A Large-Scale Dataset of Minecraft Demonstrations

The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched less. As demonstrated in the computer vision and natural language processing communities, large-scale datasets have the capacity to facilitate research by serving as an experimental and benchmarking platform for new methods. However, existing datasets compatible with reinforcement learning simulators do not have sufficient scale, structure, and quality to enable the further development and evaluation of methods focused on using human examples. Therefore, we introduce a comprehensive, large-scale, simulator-paired dataset of human demonstrations: MineRL. The dataset consists of over 60 million automatically annotated state-action pairs across a variety of related tasks in Minecraft, a dynamic, 3D, open-world environment. We present a novel data collection scheme which allows for the ongoing introduction of new tasks and the gathering of complete state information suitable for a variety of methods. We demonstrate the hierarchality, diversity, and scale of the MineRL dataset. Further, we show the difficulty of the Minecraft domain along with the potential of MineRL in developing techniques to solve key research challenges within it.

cs.LG↗

arXiv2019

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

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." We improve interpretability of reinforcement learning by increasing the utility of decision tree policies learned via reinforcement learning. These policies consist of a decision tree over the state space, which requires fewer parameters to express than traditional policy representations. Existing methods for creating decision tree policies via reinforcement learning focus on accurately representing an action-value function during training, but this leads to much larger trees than would otherwise be required. To address this shortcoming, we propose a novel algorithm which only increases tree size when the estimated discounted future reward of the overall policy would increase by a sufficient amount. Through evaluation in a simulated environment, we show that its performance is comparable or superior to traditional tree-based approaches and that it yields a more succinct policy. Additionally, we discuss tuning parameters to control the tradeoff between optimizing for smaller tree size or for overall reward.

cs.LG↗

arXiv2019

Generation of Policy-Level Explanations for Reinforcement Learning

Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current work in explainable deep learning focuses on explaining only a single decision in terms of input features, making it unsuitable for explaining a sequence of decisions. To address this need, we introduce Abstracted Policy Graphs, which are Markov chains of abstract states. This representation concisely summarizes a policy so that individual decisions can be explained in the context of expected future transitions. Additionally, we propose a method to generate these Abstracted Policy Graphs for deterministic policies given a learned value function and a set of observed transitions, potentially off-policy transitions used during training. Since no restrictions are placed on how the value function is generated, our method is compatible with many existing reinforcement learning methods. We prove that the worst-case time complexity of our method is quadratic in the number of features and linear in the number of provided transitions, $O(|F|^2 |tr\_samples|)$. By applying our method to a family of domains, we show that our method scales well in practice and produces Abstracted Policy Graphs which reliably capture relationships within these domains.

cs.LG↗

arXiv2018

Proceedings of the Workshop on Social Robots in Therapy: Focusing on Autonomy and Ethical Challenges

Robot-Assisted Therapy (RAT) has successfully been used in HRI research by including social robots in health-care interventions by virtue of their ability to engage human users both social and emotional dimensions. Research projects on this topic exist all over the globe in the USA, Europe, and Asia. All of these projects have the overall ambitious goal to increase the well-being of a vulnerable population. Typical work in RAT is performed using remote controlled robots; a technique called Wizard-of-Oz (WoZ). The robot is usually controlled, unbeknownst to the patient, by a human operator. However, WoZ has been demonstrated to not be a sustainable technique in the long-term. Providing the robots with autonomy (while remaining under the supervision of the therapist) has the potential to lighten the therapists burden, not only in the therapeutic session itself but also in longer-term diagnostic tasks. Therefore, there is a need for exploring several degrees of autonomy in social robots used in therapy. Increasing the autonomy of robots might also bring about a new set of challenges. In particular, there will be a need to answer new ethical questions regarding the use of robots with a vulnerable population, as well as a need to ensure ethically-compliant robot behaviours. Therefore, in this workshop we want to gather findings and explore which degree of autonomy might help to improve health-care interventions and how we can overcome the ethical challenges inherent to it.

cs.RO↗

arXiv2018

What Can This Robot Do? Learning from Appearance and Experiments

When presented with an unknown robot (subject) how can an autonomous agent (learner) figure out what this new robot can do? The subject's appearance can provide cues to its physical as well as cognitive capabilities. Seeing a humanoid can make one wonder if it can kick balls, climb stairs or recognize faces. What if the learner can request the subject to perform these tasks? 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. Apart from the subject's inherent capabilities, certain extrinsic factors may affect its performance at a task. Based on the subject's appearance and prior knowledge about the task a learner can identify a set of potential factors, a subset of which we assume are controllable. Our approach picks values of controllable factors to generate the most informative experiments to test the subject at. Additionally, we present a metric to determine if a factor should be incorporated in the model. We present results of our approach on modeling a humanoid robot at the task of kicking a ball. Firstly, we show that actively picking values for controllable factors, even in noisy experiments, leads to faster learning of the subject's model for the task. Secondly, starting from a minimal set of factors our metric identifies the set of relevant factors to incorporate in the model. Lastly, we show that the refined model better represents the subject's performance at the task.

cs.AI↗

arXiv2018

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

With the rapid development of robot and other intelligent and autonomous agents, how a human could be influenced by a robot's expressed mood when making decisions becomes a crucial question in human-robot interaction. 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. More specifically, we create an NLP model to generate sentences that adhere to a specific affective expression profile. We use these sentences for a humanoid robot as it plays a Stackelberg security game against a human. We investigate the behavioral model of the human player.

cs.HC↗

arXiv2018

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

With the success of deep learning, recent efforts have been focused on analyzing how learned networks make their classifications. We are interested in analyzing the network output based on the network structure and information flow through the network layers. We contribute an algorithm for 1) analyzing a deep network to find neurons that are 'important' in terms of the network classification outcome, and 2)automatically labeling the patches of the input image that activate these important neurons. We propose several measures of importance for neurons and demonstrate that our technique can be used to gain insight into, and explain how a network decomposes an image to make its final classification.

cs.LG↗