88 citations · 105 across the 10 of their papers we have counts for
11 papers
QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control
Zhehui Huang, Sumeet Batra, Tao Chen +7
Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of envir…
Cognitive Architecture for Decision-Making Based on Brain Principles Programming (in Russian)
Anton Kolonin, Andrey Kurpatov, Artem Molchanov +1
We describe a cognitive architecture intended to solve a wide range of problems based on the five identified principles of brain activity, with their implementation in three subsys…
Brain Principles Programming
Evgenii Vityaev, Anton Kolonin, Andrey Kurpatov +1
In the monograph, STRONG ARTIFICIAL INTELLIGENCE. On the Approaches to Superintelligence, published by Sberbank, provides a cross-disciplinary review of general artificial intellig…
Cognitive Architecture for Decision-Making Based on Brain Principles Programming
Anton Kolonin, Andrey Kurpatov, Artem Molchanov +1
We describe a cognitive architecture intended to solve a wide range of problems based on the five identified principles of brain activity, with their implementation in three subsys…
PredictionNet: Real-Time Joint Probabilistic Traffic Prediction for Planning, Control, and Simulation
Alexey Kamenev, Lirui Wang, Ollin Boer Bohan +6
Predicting the future motion of traffic agents is crucial for safe and efficient autonomous driving. To this end, we present PredictionNet, a deep neural network (DNN) that predict…
Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning
Sumeet Batra, Zhehui Huang, Aleksei Petrenko +3
We demonstrate the possibility of learning drone swarm controllers that are zero-shot transferable to real quadrotors via large-scale multi-agent end-to-end reinforcement learning.…
Generalized Inner Loop Meta-Learning
Edward Grefenstette, Brandon Amos, Denis Yarats +6
Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimiza…
Meta-Learning via Learned Loss
Sarah Bechtle, Artem Molchanov, Yevgen Chebotar +4
Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper…
Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors
Artem Molchanov, Tao Chen, Wolfgang Hönig +3
Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remar…
Region Growing Curriculum Generation for Reinforcement Learning
Artem Molchanov, Karol Hausman, Stan Birchfield +1
Learning a policy capable of moving an agent between any two states in the environment is important for many robotics problems involving navigation and manipulation. Due to the spa…
Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations
Jonathan Tremblay, Thang To, Artem Molchanov +3
We present a system to infer and execute a human-readable program from a real-world demonstration. The system consists of a series of neural networks to perform perception, program…