agakshat

maddpg

Implementation of Multi-Agent Deep Deterministic Policy Gradients

LOLA-pytorch

Implementing the Learning with Opponent Learning Awareness paper (https://blog.openai.com/learning-to-model-other-minds/)

AerialRobotics

Contains files for the Aerial Robotics MOOC on Coursera, taught by Prof Vijay Kumar at UPenn

visualdialog-pytorch

Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359

spacefortress

OpenAI Gym compatible reinforcement learning environment for Space Fortress https://arxiv.org/abs/1809.02206

ballbot

Optimal Control and Trajectory Tracking for the Ballbot (Nagarajan et al. 2014)

gym_vecenv

Python3 wrapper for running multiple OpenAI Gym environments in parallel

dagger-pg

Imitation Learning (DAgger) and Policy Gradients (Reinforce, A2C) in PyTorch

emerging-markets

Code used to analyze the political impact of economic institutions, specifically how regime transitions affect growth of GDP and capital

tensorflow-ddpg

Implementation of Deep Deterministic Policy Gradients using Tensorflow with Keras

multiagent-particle-envs

mvp-classifier

Code for training and testing the MVP classifier

pymarl

Beta code release for Python Multi-Agent Reinforcement Learning framework

agakshat.github.io

My home page

alexa-avs-raspberry-pi

This project demonstrates how to access and test the Alexa Voice Service using a Java client (running on a Raspberry Pi), and a Node.js server.

DeepRL

Highly modularized implementation of popular deep RL algorithms by PyTorch

docs

Documentation for Docker Official Images in docker-library

easy21

Implementation of various reinforcement learning methods on the Easy21 game, for David Silver's course

evidence-accumulation

Code for safer reinforcement learning by evidence accumulation

genai_api_playground

Play around with the capabilities of available LLMs through their APIs

genaibasics

Catch up on advances in generative AI, including LLMs, diffusion models, etc.

neurohackathon

opencv

Open Source Computer Vision Library

OpenFace

OpenFace – a state-of-the art open source tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

qnets

Q-networks for homework assignment of Deep Reinforcement Learning (10703) at CMU

sar_robot_translation

Node that translates generic robot commands to platform-specific robot commands

Thruster-Library-for-ROS

ROS node for controlling a thruster, written in Python