Anirudh Vemula's Projects
Gaussian processes framework in python
An OpenAI gym environment for the Kuka arm.
Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"
Helloworld programs in different languages,pull requests are welcome :)
Heuristic guided RRT* from the report "Learning Motion Planning Assumptions"
Iterative LQR for a differential drive robot C++
Code for experiments regarding importance sampling for training neural networks
Compiling institute events calender using event mails
(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation
Basic Information Retrieval models implemented (with Ontology-based model as well)
Papers relevant to Inverse Reinforcement learning/ Inverse Optimal Control/ Apprenticeship learning
IRL Toolkit developed by Sergey Levine (Taken from https://graphics.stanford.edu/projects/gpirl/)
Python package for IRL worlds
A Probabilistic Model for Planar Sliding of Objects with Unknown Material Properties
Keras + Gaussian Processes: Learning scalable deep and recurrent kernels.
Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"
Experiments for the paper A Lagrangian Method for Inverse Problems in Reinforcement Learning.
A repository to store all latex templates I use
A differentiable LCP physics engine in PyTorch.
Forked from the bitbucket repo: https://bitbucket.org/sanjiban/list_prediction_motion_planning
My version of the github repo https://github.com/MatthewJA/Inverse-Reinforcement-Learning by Matthew
Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"
Minimax Model Learning
Models built with TensorFlow
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.