Unsupervised Predictive Memory in a Goal-Directed Agent
نویسندگان
چکیده
Goal-Directed Agent Greg Wayne∗,1, Chia-Chun Hung∗,1, David Amos∗,1, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwińska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap. DeepMind, 5 New Street Square, London EC4A 3TW, UK. ∗These authors contributed equally to this work.
منابع مشابه
Goal-directed learning of features and forward models
The brain is able to perform actions based on an adequate internal representation of the world, where task-irrelevant features are ignored and incomplete sensory data are estimated. Traditionally, it is assumed that such abstract state representations are obtained purely from the statistics of sensory input for example by unsupervised learning methods. However, more recent findings suggest an i...
متن کاملAn Unsupervised Learning Method for an Attacker Agent in Robot Soccer Competitions Based on the Kohonen Neural Network
RoboCup competition as a great test-bed, has turned to a worldwide popular domains in recent years. The main object of such competitions is to deal with complex behavior of systems whichconsist of multiple autonomous agents. The rich experience of human soccer player can be used as a valuable reference for a robot soccer player. However, because of the differences between real and simulated soc...
متن کاملUtilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملCooperative Control of Mobile Robots in Creating a Runway Platform for Quadrotor Landing
Multi-agent systems are systems in which several agents accomplish a mission in a cooperative manner. In this paper, a novel idea for the construction of a movable runway platform based on multi-agent systems is presented. It is assumed that an aerial agent (quadrotor) decides to make an emergency landing due to reasons such as a decrease in energy level or technical failure, while there is no ...
متن کاملA hybrid generative and predictive model of the motor cortex
We describe a hybrid generative and predictive model of the motor cortex. The generative model is related to the hierarchically directed cortico-cortical (or thalamo-cortical) connections and unsupervised training leads to a topographic and sparse hidden representation of its sensory and motor input. The predictive model is related to lateral intra-area and inter-area cortical connections, func...
متن کامل