Ankur-Deka

A-Star

Simple Visual A-Star

ankur-deka.github.io

Website to describe my projects

Coding

Coding in CPP and Python

Emergent-Multiagent-Strategies

Emergence of complex strategies through multiagent competition

Hiding-Leader-Identity

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

Human-Trajectory-Prediction

Predict future trajectory in crowd

Machine-Learning-Notebooks

Simple Experiments mainly on Machine Learning

PyTorch-with-ROS-Installation-Guide

Get Anaconda and ROS running together on Ubuntu 16.04

Stable-Baselines-Interface

Interface to run RL algorithms using Stable-Baselines3

0shot-object-insertion

Simulation and robot code for contact-rich household object insertion (ICRA 2023).

Ankur-Deka/Emergent-Multiagent-Strategies

Emergence of complex strategies through multiagent competition

Ankur-Deka/PyTorch-with-ROS-Installation-Guide

Get Anaconda and ROS running together on Ubuntu 16.04

Ankur-Deka/Hiding-Leader-Identity

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

Ankur-Deka/Machine-Learning-Notebooks

Simple Experiments mainly on Machine Learning

Ankur-Deka/A-Star

Simple Visual A-Star

Ankur-Deka/ankur-deka.github.io

Website to describe my projects

Ankur-Deka/Coding

Coding in CPP and Python

Ankur-Deka/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

PyTorch implementations of deep reinforcement learning algorithms and environments

Ankur-Deka/Video-preview-tool

Preview multiple videos together

Ankur-Deka/Actor-Residual-Critic

ARC - Actor Residual Critic for Adversarial Imitation Learning

Ankur-Deka/agents

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

Ankur-Deka/CMU-RI-Presentation-Template

Unofficial PowerPoint presentation template for CMU Robotics Institute

Ankur-Deka/f-IRL

Inverse Reinforcement Learning via State Marginal Matching - CoRL 2020

Ankur-Deka/gym

A toolkit for developing and comparing reinforcement learning algorithms.

Ankur-Deka/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.

Ankur-Deka/kinova-ros

ROS packages for Jaco2 and Mico robotic arms

Ankur-Deka/MAAC

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

Ankur-Deka/magenta

Magenta: Music and Art Generation with Machine Intelligence

Ankur-Deka/marl_transfer

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

Ankur-Deka/MLFlow-Tutorial

Minimal MLFlow example for tracking ML experiments

Ankur-Deka/moveit_tutorials

A sphinx-based centralized documentation repo for MoveIt

Ankur-Deka/music-generation

Ankur-Deka/overcoming-catastrophic

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

Ankur-Deka/private_flocking

Ankur-Deka/Procedural-painting

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

Ankur-Deka/rllab

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

Ankur-Deka/ROMA

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

Ankur-Deka/simExtROSInterface

Ankur-Deka/Simple-CUDA

Simple examples to get started with CUDA Programming

Ankur-Deka/visual-pushing-grasping

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