Publications (5)
B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency
Cherish Puniani, Tushar Kumar, Arnav Bendre +2
Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in…
Grounding-Tracking-Integration
Zhengyuan Yang, Tushar Kumar, Tianlang Chen +2
In this paper, we study Tracking by Language that localizes the target box sequence in a video based on a language query. We propose a framework called GTI that decomposes the prob…
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.…
Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning
Aleksei Petrenko, Zhehui Huang, Tushar Kumar +2
Increasing the scale of reinforcement learning experiments has allowed researchers to achieve unprecedented results in both training sophisticated agents for video games, and in si…
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…