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.
We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops.
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.
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.
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.
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.
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
Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years.
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.
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.