Name: Vidyasagar Sadhu
Type: User
Company: SRI International
Bio: I am passionate about research being done at the intersection of deep learning (CNNs, LSTMs), reinforcement learning (e.g., A3C, TRPO) and multi-agent systems.
Twitter: vshssvs7
Location: Menlo Park, CA, USA
Vidyasagar Sadhu's Projects
Augmented Random Search on OpenAi gym's BipedalWalker environment.
This is the source code of "Efficient training techniques for multi-agent reinforcement learning in combatant tasks".
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
My Android Apps
Fixes macOS Preview garbled annotations
PITI: Pretraining is All You Need for Image-to-Image Translation
My public python/pycharm projects
Compute FID scores with PyTorch.
Rainbow: Combining Improvements in Deep Reinforcement Learning
An implementation of the Residual Flow algorithm for out-of-distribution detection.
The correct way to resize images or tensors. For Numpy or Pytorch (differentiable).
RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
Deep Reinforcement Learning Using AirSim and Keras
Implementation of OpenCV and DL to automate car in simulator provided by Udacity.
This repo is for demonstration purposes only.
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
The ultimate Vim configuration: vimrc
Vidyasagar Sadhu Website