Ankur Deka's Projects
Implementation of 6-DoF GraspNet with tensorflow and python. This repo has been tested with python 2.7 and tensorflow 1.12.
Simple Visual A-Star
ARC - Actor Residual Critic for Adversarial Imitation Learning
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Website to describe my projects
Encoder Decoder architecture for MNIST Compression
My repository for the Carvana Image Masking Challenge
Unofficial PowerPoint presentation template for CMU Robotics Institute
Coding in CPP and Python
Convert Data into usable format
Generic Module for Creating Image Dataset
Implementation of popular DS and Algo
PyTorch implementations of deep reinforcement learning algorithms and environments
Emergence of complex strategies through multiagent competition
Inverse Reinforcement Learning via State Marginal Matching - CoRL 2020
A toolkit for developing and comparing reinforcement learning algorithms.
Code for fabric smoothing https://sites.google.com/view/fabric-smoothing. No further updates are expected.
gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of CogSci 2020 conference award in computational modelling.
Python3 wrapper for running multiple OpenAI Gym environments in parallel
IROS 2021 - Hiding Leader’s Identity in Leader-Follower Navigation through MARL
Predict future trajectory in crowd
Solutions for coding questions in CMU 18661 assignments: Introduction to Machine Learning
ROS packages for Jaco2 and Mico robotic arms
Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019
Simple Experiments mainly on Machine Learning
PyTorch Implementation of MADDPG (Lowe et. al. 2017)
Magenta: Music and Art Generation with Machine Intelligence
A Multi-agent Learning Framework
Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)
Minimal MLFlow example for tracking ML experiments