Junyeob Baek
dion-jy
PhD Student @ KAIST / Interested in crafting lifelong developmental agents 🤖
Languages
Top Repositories
paper-list of learning-based mobile navigation(especially motion planning & awareness)
A Simple Pytorch Implementation of LSTM-based Variational Autoencoder(VAE)
Pytorch Implementation of Policy Distillation for control, which has well-trained teachers via stable_baselines3.
road-map & paper review for Reinforcement Learning
Keras Implementation of DDPG(Deep Deterministic Policy Gradient) with PER(Prioritized Experience Replay) option on OpenAI gym framework
Keras Implementation of TD3(Twin Delayed DDPG) with PER(Prioritized Experience Replay) option on OpenAI gym framework
Repositories
33🎵 Rondo — Cron monitoring dashboard for OpenClaw (Vercel frontend)
Cron job calendar view + real-time monitoring + editing
Squeeze your productivity. Monitor your Claude.ai usage in real-time.
No description provided.
Pytorch Implementation of Policy Distillation for control, which has well-trained teachers via stable_baselines3.
CADAM + Assembly Mode for BodyPrint
Claude usage widget for Windows
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
My personal profile
Manage multiple AI terminal agents like Claude Code, Aider, Codex, OpenCode, and Amp.
AI research skills for Claude Code — experiment launching, wandb integration, and training workflows
A Simple Pytorch Implementation of LSTM-based Variational Autoencoder(VAE)
road-map & paper review for Reinforcement Learning
paper-list of learning-based mobile navigation(especially motion planning & awareness)
No description provided.
Keras Implementation of TD3(Twin Delayed DDPG) with PER(Prioritized Experience Replay) option on OpenAI gym framework
No description provided.
Keras Implementation of DDPG(Deep Deterministic Policy Gradient) with PER(Prioritized Experience Replay) option on OpenAI gym framework
No description provided.
WalkYTo-rl-gym Environment. Walk Yourself, Toddler! Toddlers can learn by deep reinforcement learning now.
A simple pytorch implementation of Adversarial Autoencoder(AAE)
Code for our CVPR 2022 paper 'Generalized Category Discovery'. Project page: https://www.robots.ox.ac.uk/~vgg/research/gcd/
unofficial backup service for mpi3d_real dataset
No description provided.
My Personal Site
Simple Codebases for Benchmarking Object-Centric Architectures
No description provided.
A toolkit for developing and comparing reinforcement learning algorithms.
Keras implementation of convolutional autoencoder architecture, and example test with MNIST
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.