- Palo Alto
- https://cs.cmu.edu/~khusha
Highlights
- Pro
Stars
Code Release for floq: Training Critics via Flow-Matching for Scaling Compute In Value-Based RL
A benchmark for offline goal-conditioned RL and offline RL
Skeleton for scalable and flexible Jax RL implementations
PyTorch - Implicit Quantile Networks - Quantile Regression - C51
Python sample codes and textbook for robotics algorithms.
Source free Single and Multi target Unsupervised Domain Adaptation
A Tensorboard plugin that allows you to rename and delete log folders.
Code for the CoRL 2021 paper "FabricFlowNet: Bimanual Manipulation using a Flow-based Policy"
Pytorch implementation of Model Predictive Control with learned models
A fast and differentiable model predictive control (MPC) solver for PyTorch.
Isaac Gym Reinforcement Learning Environments
Wrappers and utilities for Nvidia IsaacGym
Efficiently sampling vectors from the n-sphere and n-ball
Tiny library for rotating vectors in N dimensions
Curated list of awesome advice, tips, and resources to prepare for PhD/grad school.
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)
Software for LOCO, our autonomous drifting RC car.
Version 3 of Autonomous Stair Climbing Robot
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
RLtime is a reinforcement learning library focused on state-of-the-art q-learning algorithms and features
Collection of reinforcement learning algorithms
⏰ AI conference deadline countdowns
Resources on various topics being worked on at IvLabs
An elegant PyTorch deep reinforcement learning library.
Modular implementation of yolo-v3 detection algorithm
Code implementation of Data Efficient Stagewise Knowledge Distillation paper.