naivoder

A3C

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) with parallel learning

algorithms

Solutions to interesting problems, implementations of abstract data types and fundamental algorithms, benchmarks and more. Having fun with python!

DCVAE

Keras implementation of a deep convolutional variational autoencoder (DCVAE) evaluated on the MNIST dataset

DDPG

Pytorch implementation of Deep Deterministic Policy Gradients (DDPG)

DigitalTwin

ROS digital twin simulation, inverse kinematic trajectory planning, collision avoidance and local network communication using UR10 manipulator.

DQN

Pytorch implementation of Deep Q Network (DQN) learning with vectorized environments

dreamerv3

PyTorch implementation of DreamerV3 from "Mastering Diverse Domains with World Models"

feeder

Intelligent pest control application - CNN and water turret to defend bird feeder from squirrels

MCTSr

Monte Carlo Tree Search Self-Refine (MCTSr)

SAC

Pytorch Implementation of Soft Actor Critic (SAC)

naivoder/MCTSr

Monte Carlo Tree Search Self-Refine (MCTSr)

naivoder/DDPG

Pytorch implementation of Deep Deterministic Policy Gradients (DDPG)

naivoder/DQN

Pytorch implementation of Deep Q Network (DQN) learning with vectorized environments

naivoder/dreamerv3

PyTorch implementation of DreamerV3 from "Mastering Diverse Domains with World Models"

naivoder/A3C

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) with parallel learning

naivoder/ascii_cards

ASCII art representations of playing cards

naivoder/AttentionIsAllYouNeed

PyTorch implementation of transformers with multi-headed self attention

naivoder/DDQN

Pytorch implementation of Double Deep Q Network (DDQN) learning with vectorized environments

naivoder/DuelingDDQN

PyTorch implementation of Dueling Double Deep Q-Learning (Dueling DDQN) for Atari environments

naivoder/PPO

Pytorch implementation of Proximal Policy Optimization (PPO) for continuous action spaces

naivoder/reinforcement_learning

Implementations of various Reinforcement Learning algorithms in Python

naivoder/SAC

Pytorch Implementation of Soft Actor Critic (SAC)

naivoder/TD3

Pytorch implementation of twin delayed deep deterministic policy gradients (TD3)

naivoder/CTRL-F

Pytorch implementation of CTRL-F: pairing convolution with transformer for image classification via multi-level feature cross-attention and representation learning fusion

naivoder/DebugRL

"Minimalistic Gymnasium environments for debugging RL algorithms"

naivoder/DeformableCapsuleNetwork

Pytorch implementation of Deformable Capsule Networks (DeformCaps) for object detection

naivoder/DiscretePPO

Pytorch implementation of Proximal Policy Optimization (PPO) for discrete action spaces

naivoder/dreamerv2

naivoder/dreamerv3-jax

Mastering Diverse Domains through World Models

naivoder/DreamWeaver

Continual Meta-Reinforcement Learning for Operating System Optimization Tasks with a Shared World Model and Adaptive Compositional Policy Initializations

naivoder/ICM

PyTorch implementation of A3C with Intrinsic Curiosity Module (ICM) evaluated on Miniworld and Atari environments

naivoder/ImageToCartoon

Simple script to make images look like cartoon animations

naivoder/LaplacianNet

Laplacian Image Pyramid Convolutional Neural Network

naivoder/math-ml

teaching agents to do math from scratch

naivoder/park

OS Reinforcement Learning Environments

naivoder/REINFORCE

PyTorch implementation of Monte Carlo policy gradient reinforcement

naivoder/ROS2_experiments

naivoder/SubtractNet

This network repeatedly takes the difference between parallel streams of convolutional blocks

naivoder/ViTCapsuleNet

Hybrid Vision Transformer (ViT) Capsule Network

naivoder/WeirdNets

A collection of strange neural network architectures, just for fun!