Ankur-Deka

Emergent-Multiagent-Strategies

Emergence of complex strategies through multiagent competition

PyTorch-with-ROS-Installation-Guide

Get Anaconda and ROS running together on Ubuntu 16.04

Hiding-Leader-Identity

IROS 2021 - Hiding Leader’s Identity in Leader-Follower Navigation through MARL

Machine-Learning-Notebooks

Simple Experiments mainly on Machine Learning

A-Star

Simple Visual A-Star

ankur-deka.github.io

Website to describe my projects

Coding

Coding in CPP and Python

Deep-Reinforcement-Learning-Algorithms-with-PyTorch

PyTorch implementations of deep reinforcement learning algorithms and environments

maddpg-pytorch

PyTorch Implementation of MADDPG (Lowe et. al. 2017)

Video-preview-tool

Preview multiple videos together

Actor-Residual-Critic

ARC - Actor Residual Critic for Adversarial Imitation Learning

agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

CMU-RI-Presentation-Template

Unofficial PowerPoint presentation template for CMU Robotics Institute

f-IRL

Inverse Reinforcement Learning via State Marginal Matching - CoRL 2020

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-cooking

gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of CogSci 2020 conference award in computational modelling.

kinova-ros

ROS packages for Jaco2 and Mico robotic arms

MAAC

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

magenta

Magenta: Music and Art Generation with Machine Intelligence

marl_transfer

Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)

MLFlow-Tutorial

Minimal MLFlow example for tracking ML experiments

moveit_tutorials

A sphinx-based centralized documentation repo for MoveIt

music-generation

overcoming-catastrophic

Implementation of "Overcoming catastrophic forgetting in neural networks" in Tensorflow

private_flocking

Procedural-painting

Procedural painting algorithms in Unity 3d with compute shaders based on genetic evolution algorithms

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

ROMA

Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)

simExtROSInterface

visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.