Nishant Kumar's repositories
guided-cost-learning
Implementation of the paper https://arxiv.org/abs/1603.00448.
federated-model-averaging-for-DQN
In this work, we propose a novel formulation titled Federated Deep Q Networks (F-DQN) to perform distributed learning for Deep RL algorithms.
GSoC-2020-mlpack
Contains weekly updates for my proposal on Implementing RL methods in mlpack.
FlappyBirdOnJavascript
FlappyBird agent learns to master the game using Neuroevolution!
RLOS-2021-Microsoft
Contains updates for my work on Parallel parsing improvements on Vowpal Wabbit.
cops_namecards
COPS Repository for Contributors Namecards
flask-hello-world
Flask Hello World Example for Render
Flowise
Drag & drop UI to build your customized LLM flow
gym_tcp_api
gym tcp api
IIT-BHU-app
The official app for managing activities at the Indian Institute of Technology (BHU), Varanasi.
langchain
⚡ Building applications with LLMs through composability ⚡
mail-using-doc
A python script that can read multiple txt files you provide, and answer your question by selecting the most relevant txt file, in the form of a mail.
my-chatbots
a list of Chat bots using GPT and streamlit.
option-critic-pytorch
PyTorch implementation of the Option-Critic framework, Harb et al. 2016
PettingZoo
Gym for multi-agent reinforcement learning
titus-awesome
Custom AwesomeWM Theme
vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.