simonszalai

Creative-Destruction-Quantum-Hackathon-2022

CDL Quantum Hackathon 2022

ddpg-continuous-control-udacity

Deep Deterministic Policy Gradients reinforcement learning algorithm to solve a continuous control environment

ddpg-multi-agent-udacity

deep-active-inference-mc

Deep active inference agents using Monte-Carlo methods

deep-q-learning-discrete-control-udacity

diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

sorterbot_cloud

Cloud service for the SorterBot project, which contains the neural networks and other compute-heavy tasks needed for image processing.

sorterbot_control

Control Panel for the SorterBot project to serve the UI, manage the database, and handle the websocket connections to the Raspberry PIs.

sorterbot_installer

A combination of AWS CDK and bash scripts to provide single-command deploy/destroy functionality for the SorterBot project.

sorterbot_raspberry

Part of the SorterBot project. This repo contains the Python script which runs on the Raspberry PIs and controls the Pi Camera, Robotic Arm and manages the websocket connections.

simonszalai/sorterbot_raspberry

Part of the SorterBot project. This repo contains the Python script which runs on the Raspberry PIs and controls the Pi Camera, Robotic Arm and manages the websocket connections.

simonszalai/sorterbot_cloud

Cloud service for the SorterBot project, which contains the neural networks and other compute-heavy tasks needed for image processing.

simonszalai/sorterbot_control

Control Panel for the SorterBot project to serve the UI, manage the database, and handle the websocket connections to the Raspberry PIs.

simonszalai/sorterbot_installer

A combination of AWS CDK and bash scripts to provide single-command deploy/destroy functionality for the SorterBot project.

simonszalai/Creative-Destruction-Quantum-Hackathon-2022

CDL Quantum Hackathon 2022

simonszalai/ddpg-continuous-control-udacity

Deep Deterministic Policy Gradients reinforcement learning algorithm to solve a continuous control environment

simonszalai/ddpg-multi-agent-udacity

simonszalai/deep-active-inference-mc

Deep active inference agents using Monte-Carlo methods

simonszalai/deep-q-learning-discrete-control-udacity

simonszalai/diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

simonszalai/goa-stack

simonszalai/mantine_repro

simonszalai/minGPT

minGPT in JAX

simonszalai/qosf-assessment

simonszalai/sorterbot_labeltool

Labeling tool for training dataset creation for the SorterBot project.