Pinned Repositories
assignment4
I am open sourcing the boiler plate code necessary for Assignment 4 so we can focus on the analysis instead.
BasicVAE
Personal project on creating a VAE for image data (MNIST) using only Multilayer Perceptrons. This project was inspired by a CSCI 599 assignment for creating VAEs (https://github.com/shaohua0116/VAE-Tensorflow)
CityPark
App that helps you park your car in the city
deformable-ravens
Code for: https://berkeleyautomation.github.io/bags/
gym_envs
OpenAI gym reacher environment with improved reward function
IRLTutorial
Example code for my tutorial on inverse reinforcement learning
OccupancyGrid
My prototype for an occupancy grid framework in MATLAB.
rl-baselines-zoo
A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
Simulation-and-Control-of-a-Stanford-Arm
Course project for ME384R: Advanced Dynamics of Robotic Systems
BasicPOMCP.jl
The PO-UCT algorithm (aka POMCP) implemented in Julia
gautams3's Repositories
gautams3/Simulation-and-Control-of-a-Stanford-Arm
Course project for ME384R: Advanced Dynamics of Robotic Systems
gautams3/OccupancyGrid
My prototype for an occupancy grid framework in MATLAB.
gautams3/IRLTutorial
Example code for my tutorial on inverse reinforcement learning
gautams3/assignment4
I am open sourcing the boiler plate code necessary for Assignment 4 so we can focus on the analysis instead.
gautams3/BasicVAE
Personal project on creating a VAE for image data (MNIST) using only Multilayer Perceptrons. This project was inspired by a CSCI 599 assignment for creating VAEs (https://github.com/shaohua0116/VAE-Tensorflow)
gautams3/CityPark
App that helps you park your car in the city
gautams3/deformable-ravens
Code for: https://berkeleyautomation.github.io/bags/
gautams3/dmfd_rlds_dataset_builder
RLDS dataset builder for DMfD, for the X-embodiment dataset conversion.
gautams3/gym_envs
OpenAI gym reacher environment with improved reward function
gautams3/IRL_IntelligentGrading
Using Inverse Reinforcement Learning for grading of physical (sensorimotor) skills. This framework is a proof-of-concept with a toy problem of navigating in grid-based parking lot
gautams3/rl-baselines-zoo
A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.
gautams3/sample-factory
High throughput asynchronous reinforcement learning
gautams3/serl
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
gautams3/tiny-differentiable-simulator
Tiny Differentiable Simulator is a header-only C++ physics library with zero dependencies.