Search Results for author: Raul Vicente

Found 12 papers, 7 papers with code

Mind the gap: Challenges of deep learning approaches to Theory of Mind

no code implementations30 Mar 2022 Jaan Aru, Aqeel Labash, Oriol Corcoll, Raul Vicente

Theory of Mind is an essential ability of humans to infer the mental states of others.

Did I do that? Blame as a means to identify controlled effects in reinforcement learning

1 code implementation ICML Workshop URL 2021 Oriol Corcoll, Youssef Mohamed, Raul Vicente

This work proposes Controlled Effect Network (CEN), an unsupervised method based on counterfactual measures of blame to identify effects on the environment controlled by the agent.

Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops

1 code implementation19 Nov 2020 Florian Stelzer, André Röhm, Raul Vicente, Ingo Fischer, Serhiy Yanchuk

We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops.

Disentangling causal effects for hierarchical reinforcement learning

no code implementations3 Oct 2020 Oriol Corcoll, Raul Vicente

This distribution is used by a high-level policy to 1) explore the environment via random effect exploration so that novel effects are continuously discovered and learned, and to 2) learn task-specific behavior by prioritizing the effects that maximize a given reward function.

Hierarchical Reinforcement Learning reinforcement-learning

The many faces of deep learning

no code implementations25 Aug 2019 Raul Vicente

This diversity of perspectives on deep learning, from neuroscience to statistical physics, is a rich source of inspiration that fuels novel developments in the theory and applications of machine learning.

Direct information transfer rate optimisation for SSVEP-based BCI

1 code implementation19 Jul 2019 Anti Ingel, Ilya Kuzovkin, Raul Vicente

The proposed method shows good performance in classifying targets of a BCI, outperforming previously reported results on the same dataset by a factor of 2 in terms of ITR.

General Classification

Perspective Taking in Deep Reinforcement Learning Agents

no code implementations3 Jul 2019 Aqeel Labash, Jaan Aru, Tambet Matiisen, Ardi Tampuu, Raul Vicente

We believe that, in the long run, building better artificial agents with perspective taking ability can help us develop artificial intelligence that is more human-like and easier to communicate with.

reinforcement-learning

MAXENT3D_PID: An Estimator for the Maximum-entropy Trivariate Partial Information Decomposition

2 code implementations10 Jan 2019 Abdullah Makkeh, Daniel Chicharro, Dirk Oliver Theis, Raul Vicente

Chicharro (2017) introduced a procedure to determine multivariate partial information measures within the maximum entropy framework, separating unique, redundant, and synergistic components of information.

Computation Optimization and Control

APES: a Python toolbox for simulating reinforcement learning environments

2 code implementations31 Aug 2018 Aqeel Labash, Ardi Tampuu, Tambet Matiisen, Jaan Aru, Raul Vicente

Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years.

reinforcement-learning

Do deep reinforcement learning agents model intentions?

1 code implementation15 May 2018 Tambet Matiisen, Aqeel Labash, Daniel Majoral, Jaan Aru, Raul Vicente

In this work we test whether deep reinforcement learning agents explicitly represent other agents' intentions (their specific aims or goals) during a task in which the agents had to coordinate the covering of different spots in a 2D environment.

reinforcement-learning

What deep learning can tell us about higher cognitive functions like mindreading?

no code implementations28 Mar 2018 Jaan Aru, Raul Vicente

Can deep learning (DL) guide our understanding of computations happening in biological brain?

Object Recognition

Multiagent Cooperation and Competition with Deep Reinforcement Learning

4 code implementations27 Nov 2015 Ardi Tampuu, Tambet Matiisen, Dorian Kodelja, Ilya Kuzovkin, Kristjan Korjus, Juhan Aru, Jaan Aru, Raul Vicente

In the present work we extend the Deep Q-Learning Network architecture proposed by Google DeepMind to multiagent environments and investigate how two agents controlled by independent Deep Q-Networks interact in the classic videogame Pong.

Q-Learning reinforcement-learning

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