4 code implementations • 27 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.
no code implementations • 28 Mar 2018 • Jaan Aru, Raul Vicente
Can deep learning (DL) guide our understanding of computations happening in biological brain?
1 code implementation • 15 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.
2 code implementations • 31 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.
2 code implementations • 10 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
no code implementations • 3 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.
1 code implementation • 19 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.
no code implementations • 25 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.
no code implementations • 3 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.
1 code implementation • 19 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.
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.
no code implementations • 30 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.
1 code implementation • 22 Jul 2023 • Aqeel Labash, Florian Fletzer, Daniel Majoral, Raul Vicente
From a dynamical systems view, we demonstrate that the adaptation proceeds by the emergence of a stable periodic orbit in the neuron dynamics with a phase response that allows an optimal phase synchronisation between the agent's dynamics and the environmental rhythm.