sureli Goto Github PK

1dtrack

1-dimensional walk environment

aerobench_fixed_target_low_order

aerobench_fixed_target_star

aerobench_variable_target_low_order

aerobench_variable_target_star

ataribots

benchmark

Different benchmarks to compare the performance of RL algorithms on CPU/GPU

biblio-these-francois

Summary of approximately interesting articles read for the thesis

blog

The SuReLI blog

curiosity-es

We use intrinsic motivation with evolutionnary strategies, creating diversity without defining a behaviour.

cylinder2dflowcontroldrl

code for performing active flow control of the 2D Karman street using Deep Reinforcement Learning

deep-rl-agents

dicyr_code

Code for DiCyR: Disentangled Cyclic Reconstruction for domain adaptation

differentiablenas

Implementations of existing and new methods in Differentiable Neural Architecture Search in Julia.

drl2fly_totuto

Tutorial of DRL coupling with CFD

dyna-gym

This is a pip package implementing Reinforcement Learning algorithms in non-stationary environments supported by the OpenAI Gym toolkit.

dynamic_mcnf_paper_code

enseignement

Supports de cours

flatland

2-dimensional navigation environment

hiv_experiment

install-scripts

Installation of deep learning environment from Ubuntu

jpo_presentation

The files that were used for the presentation during the JPO

l2f-sim

The Learning to fly project's flight simulator

laber

llamn-code

llrl

Lipschitz Lifelong RL

ma_playground_env

Implementation of the Playground environment from the paper Language as a Cognitive Tool to Imagine Goals inCuriosity-Driven Exploration.

muzero

naibx-mlc

Naive Bayes for Subset Selection (NaiBX): an extension of Naive Bayes to multi-label classification

neurops

Implementations of growing and pruning in neural networks