gyu-heo
Follow
Stars
An annotated implementation of the Transformer paper.
Welcome to the Physics-based Deep Learning Book (v0.2)
JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️
Implementation of Dreamer v3 in pytorch.
Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselines.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
⚡ Flashbax: Accelerated Replay Buffers in JAX
An implementation of DreamerV2 written in JAX and Haiku.
An implementation of DreamerV2 written in JAX, with support for running multiple random seeds of an experiment on a single GPU.
Learning Robust Dynamics Through Variational Sparse Gating
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
PyTorch based implementation of model-based RL algorithm PlaNet
Evaluating long-term memory of reinforcement learning algorithms
PyTorch implementation of DreamerV2 model-based RL algorithm
Deep Planning Network: Control from pixels by latent planning with learned dynamics
Implemenation of the HIERarchical imagionation On Structured State Space Sequence Models (HIEROS) paper
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
PyTorch implementation of Episodic Meta Reinforcement Learning on variants of the "Two-Step" task. Reproduces the results found in three papers. Check the ReadMe for more details!
PlaNet: Learning Latent Dynamics for Planning from Pixels
Pytorch implementation of Dreamer-v2: Visual Model Based RL Algorithm.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Simple and easily configurable grid world environments for reinforcement learning
Code for the paper "Harnessing Discrete Representations for Continual Reinforcement Learning"
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code