timoklein

alphazero-gym

AlphaZero for continuous control tasks

redo

ReDo: The Dormant Neuron Phenomenon in Deep Reinforcement Learning (pytorch)

car_racer

Deep reinforcement learning in autonomous driving

infer

InFeR: Understanding and Preventing Capacity Loss in Reinforcement Learning (pytorch)

neural_citation

Context aware citation recommendation

crelu-pytorch

CReLU activation function from the paper "Loss of Plasticity in Continual Deep Reinforcement Learning"

implicit_underparameterization

Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning (pytorch)

ma_thesis

Combining Reinforcement Learning and Search for Cooperative Trajectory Planning

bandit_algos

Some common algorithms for multi-armed bandit problems

cleanrl

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

ClustPy

A Python library for advanced clustering algorithms

cpp_optim

Nonlinear optimization examples in C++

dmcgym

garage

A toolkit for reproducible reinforcement learning research.

HIR

markov-abstractions-ablations

DM control Markov component ablations

outlier_detection

Class based Python implementations of outlier detection algorithms.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Minigrid

Simple and easily configurable grid world environments for reinforcement learning

rl_graph_breaks

An example of torch.compile graph breaks in RL code using SAC-discrete as an example

udemy_cpp

C++ Course

wandb_tutorial

Code example for some basic wandb functionality