Prateek Bhustali

obstacle-overtaking-gpmp2. HTML

LayoutGKN. [BMVC 2025] LayoutGKN: Graph Similarity Learning of Floor Plans

msd. [ECCV 2024] MSD: A Benchmark Dataset for Floor Plan of Building Complexes

ssig. [ICCVw 2023] SSIG: A Visually-Guided Graph Edit Distance for Floor Plan Similarity

Awesome-Causal-RL. A curated list of causal reinforcement learning resources.

imp-act-JaxMARL. Adaption of JAXMARL for imp-act.

all-rl-algorithms. Implementation of all RL algorithms in a simpler way

evosax. Evolution Strategies in JAX 🦎

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

gymnax-blines. Baselines for gymnax 🤖

gymnax. RL Environments in JAX 🌍

rlbase_stable. Python

morl-baselines. Multi-Objective Reinforcement Learning algorithms implementations.

rejax. Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!

BenchMARL. BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

purejaxql. Simple single-file baselines for Q-Learning in pure-GPU setting

dreamerv2. Pytorch implementation of Dreamer-v2: Visual Model Based RL Algorithm.

epymarl. An extension of the PyMARL codebase that includes additional algorithms and environment support

Mava. 🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

jumanji. 🕹️ A diverse suite of scalable reinforcement learning environments in JAX

awesome-mlss. 🤖 Machine Learning Summer School Guide

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

MARL-Papers. Paper list of multi-agent reinforcement learning (MARL)

openrlbenchmark. Python

get-started-with-JAX. The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well as the content I found useful while learning about the JAX ecosystem.

awesome-deep-rl. A curated list of awesome Deep Reinforcement Learning resources.

awesome-jax. JAX - A curated list of resources https://github.com/google/jax

DI-engine. OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

flashbax. ⚡ Flashbax: Accelerated Replay Buffers in JAX

purejaxrl. Really Fast End-to-End Jax RL Implementations

Robust-optimal-maintenance-planning-through-reinforcement-learning-and-domain-randomization. Python

awesome-model-based-RL. A curated list of awesome model based RL resources (continually updated)

imp-act. Jupyter Notebook

JaxMARL. Multi-Agent Reinforcement Learning with JAX

MO-Gymnasium. Multi-objective Gymnasium environments for reinforcement learning

phd-resources. Not the research toolbox you deserve, but the one you need right now.

imp_marl. IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

VectorizedMultiAgentSimulator. VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

mbrl-lib. Library for Model Based RL

rl-generalization. Modifiable OpenAI Gym environments for studying generalization in RL

codebase. Official code repo for the MARL book (www.marl-book.com)

awesome-rl-envs.

FBPINNs. Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

MARLlib. One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

Multi-Agent-Reinforcement-Learning-Environment. Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

iccv23-challenge. Floor plan auto-completion on the Modified Swiss Dwellings (MSD) dataset

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

gradient_descent_viz. interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

PyOMA. Python

AI-Toolbox. A C++ framework for MDPs and POMDPs with Python bindings

mcmc-demo. Interactive Markov-chain Monte Carlo Javascript demos

latex-templates. A collection of LaTeX templates used for research, courses, and miscellanea.

gitignore. A collection of useful .gitignore templates

manim. A community-maintained Python framework for creating mathematical animations.

misbrands. The world's most hated IT stickers

deep-learning-uncertainty. Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.