Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success …
H Le, C Voloshin, Y Yue - International Conference on …, 2019 - proceedings.mlr.press
When learning policies for real-world domains, two important questions arise:(i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate …
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios. However …
We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can …
We present Neural-Swarm2, a learning-based method for motion planning and control that allows heterogeneous multirotors in a swarm to safely fly in close proximity. Such operation …
A Verma, H Le, Y Yue… - Advances in Neural …, 2019 - proceedings.neurips.cc
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more …
Current state-of-the-art sports statistics compare players and teams to league average performance. For example, metrics such as “Wins-above-Replacement”(WAR) in baseball …
In this paper, we present Neural-Swarm, a nonlinear decentralized stable controller for close- proximity flight of multirotor swarms. Close-proximity control is challenging due to the …
D Jarrett, I Bica… - Advances in Neural …, 2020 - proceedings.neurips.cc
Consider learning a policy purely on the basis of demonstrated behavior---that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further …