Search Results - "Borsa, Diana"

Detecting disease outbreaks in mass gatherings using Internet data by Yom-Tov, Elad, Borsa, Diana, Cox, Ingemar J, McKendry, Rachel A

“…Mass gatherings, such as music festivals and religious events, pose a health care challenge because of the risk of transmission of communicable diseases. This…”
Get full text

Fast reinforcement learning with generalized policy updates by Barreto, André, Hou, Shaobo, Borsa, Diana, Silver, David, Precup, Doina

“…The combination of reinforcement learning with deep learning is a promising approach to tackle important sequential decision-making problems that are currently…”
Get full text

Reinforcement Learning in Persistent Environments : Representation Learning and Transfer by Borsa, Diana

“…Reinforcement learning (RL) provides a general framework for modelling and reasoning about agents capable of sequential decision making, with the goal of…”
Get full text

Automatic identification of Web-based risk markers for health events by Yom-Tov, Elad, Borsa, Diana, Hayward, Andrew C, McKendry, Rachel A, Cox, Ingemar J

“…The escalating cost of global health care is driving the development of new technologies to identify early indicators of an individual's risk of disease…”
Get full text

A State Representation for Diminishing Rewards by Moskovitz, Ted, Hromadka, Samo, Touati, Ahmed, Borsa, Diana, Sahani, Maneesh

“…A common setting in multitask reinforcement learning (RL) demands that an agent rapidly adapt to various stationary reward functions randomly sampled from a…”
Get full text

Selective Credit Assignment by Chelu, Veronica, Borsa, Diana, Precup, Doina, van Hasselt, Hado

“…Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on…”
Get full text

When should agents explore? by Pîslar, Miruna, Szepesvari, David, Ostrovski, Georg, Borsa, Diana, Schaul, Tom

“…Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a monolithic behaviour policy that…”
Get full text

Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition by Chandak, Yash, Thakoor, Shantanu, Guo, Zhaohan Daniel, Tang, Yunhao, Munos, Remi, Dabney, Will, Borsa, Diana L

“…Representation learning and exploration are among the key challenges for any deep reinforcement learning agent. In this work, we provide a singular value…”
Get full text

Return-based Scaling: Yet Another Normalisation Trick for Deep RL by Schaul, Tom, Ostrovski, Georg, Kemaev, Iurii, Borsa, Diana

“…Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning;…”
Get full text

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning by Khetarpal, Khimya, Guo, Zhaohan Daniel, Pires, Bernardo Avila, Tang, Yunhao, Lyle, Clare, Rowland, Mark, Heess, Nicolas, Borsa, Diana, Guez, Arthur, Dabney, Will

“…Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent…”
Get full text

Generalised Policy Improvement with Geometric Policy Composition by Thakoor, Shantanu, Rowland, Mark, Borsa, Diana, Dabney, Will, Munos, Rémi, Barreto, André

“…We introduce a method for policy improvement that interpolates between the greedy approach of value-based reinforcement learning (RL) and the full planning…”
Get full text

Model-Value Inconsistency as a Signal for Epistemic Uncertainty by Filos, Angelos, Vértes, Eszter, Marinho, Zita, Farquhar, Gregory, Borsa, Diana, Friesen, Abram, Behbahani, Feryal, Schaul, Tom, Barreto, André, Osindero, Simon

“…Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths…”
Get full text

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning by Schaul, Tom, Borsa, Diana, Modayil, Joseph, Pascanu, Razvan

“…Rather than proposing a new method, this paper investigates an issue present in existing learning algorithms. We study the learning dynamics of reinforcement…”
Get full text

Expected Eligibility Traces by van Hasselt, Hado, Madjiheurem, Sephora, Hessel, Matteo, Silver, David, Barreto, André, Borsa, Diana

“…The question of how to determine which states and actions are responsible for a certain outcome is known as the credit assignment problem and remains a central…”
Get full text

Adapting Behaviour for Learning Progress by Schaul, Tom, Borsa, Diana, Ding, David, Szepesvari, David, Ostrovski, Georg, Dabney, Will, Osindero, Simon

“…Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in…”
Get full text

Conditional Importance Sampling for Off-Policy Learning by Rowland, Mark, Harutyunyan, Anna, van Hasselt, Hado, Borsa, Diana, Schaul, Tom, Munos, Rémi, Dabney, Will

“…The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance…”
Get full text

The Option Keyboard: Combining Skills in Reinforcement Learning by Barreto, André, Borsa, Diana, Hou, Shaobo, Comanici, Gheorghe, Aygün, Eser, Hamel, Philippe, Toyama, Daniel, Hunt, Jonathan, Mourad, Shibl, Silver, David, Precup, Doina

“…The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended…”
Get full text

Learning Shared Representations in Multi-task Reinforcement Learning by Borsa, Diana, Graepel, Thore, Shawe-Taylor, John

“…We investigate a paradigm in multi-task reinforcement learning (MT-RL) in which an agent is placed in an environment and needs to learn to perform a series of…”
Get full text

General non-linear Bellman equations by van Hasselt, Hado, Quan, John, Hessel, Matteo, Xu, Zhongwen, Borsa, Diana, Barreto, Andre

“…We consider a general class of non-linear Bellman equations. These open up a design space of algorithms that have interesting properties, which has two…”
Get full text

Observational Learning by Reinforcement Learning by Borsa, Diana, Piot, Bilal, Munos, Rémi, Pietquin, Olivier

“…Observational learning is a type of learning that occurs as a function of observing, retaining and possibly replicating or imitating the behaviour of another…”
Get full text