profile
viewpoint
If you are wondering where the data of this site comes from, please visit https://api.github.com/users/ingambe/events. GitMemory does not store any data, but only uses NGINX to cache data for a period of time. The idea behind GitMemory is simply to give users a better reading experience.
Pierre TASSEL ingambe University of Klagenfurt Austria http://pierretassel.fr/

prosysscience/JSSEnv 21

An OpenAi Gym environment for the Job Shop Scheduling problem.

prosysscience/RL-Job-Shop-Scheduling 13

Reinforcement learning approach for job shop scheduling

ingambe/Aircraft_Scheduling 1

PoC aircraft scheduling in ASP

ingambe/JSSEnv 1

An OpenAi Gym environment for the Job Shop Scheduling problem.

ingambe/Strongly-Connected-Component 1

A C++ implementation of the three major SCC algorithms (Gabow, Kosaraju and Tarjan).

ingambe/analyse-matrice 0

Analyse de performance d'un algorithme de calcul de produit matriciel

ingambe/Awale-Alpha-Beta 0

An Alpha Beta implementation for the game Awale (Oware)

ingambe/cleanrl 0

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features

ingambe/clingo 0

🤔 A grounder and solver for logic programs.

ingambe/deep-reinforcement-learning 0

Repo for the Deep Reinforcement Learning Nanodegree program

startediffiX/machin

started time in 14 days

push eventingambe/LearningHeuristics

Pierre Tassel

commit sha 4b3a7c9c2a68aaa3386061f7cbacde2503774503

workload balancing

view details

push time in 18 days

create barnchingambe/LearningHeuristics

branch : pdf

created branch time in 18 days

push eventingambe/LearningHeuristics

Pierre Tassel

commit sha c06d3166615f17612db64f394590a61dd62b6ae1

workload balancing

view details

push time in 18 days

push eventingambe/LearningHeuristics

Pierre Tassel

commit sha 83725f4c1841099a0bfcc5e79c35c96552a677ee

workload balancing

view details

push time in 18 days

push eventingambe/LearningHeuristics

Pierre Tassel

commit sha 472d754e6644cd4d2c1460f77c772ef30c7fce73

add ES code

view details

push time in 21 days

issue commentprosysscience/RL-Job-Shop-Scheduling

Python-Version?

Thank you for your encouraging words :) We used Python 3.8 To be more precise, our testing environment is based on google's TensorFlow 2.2 GPU docker container: gcr.io/deeplearning-platform-release/tf2-gpu.2-2 It helped us to avoid the burden of setting up everything from scratch

ClemeSto

comment created time in a month

MemberEvent

startedthu-ml/tianshou

started time in 2 months

issue commentray-project/ray

[rllib] TorchPolicy GPU not detected (IndexError)

Same problem here

juliusfrost

comment created time in 2 months

issue commentprosysscience/JSSEnv

A question about learning rate.

The actor and the critic share the same learning rate. The entropy coefficient is a term that is used to encourage exploration. I recommend you to read this paper that explore the impact of entropy on policy optimization: https://arxiv.org/abs/1811.11214

DS-cmd

comment created time in 2 months

issue commentprosysscience/JSSEnv

needhelp: Makespan and Training reward

The makespan is accessible through the current_time_step variable For plotting, it will depend on your training settings. In our paper we used RLLib, you can have a look at our code to take some inspiration: https://github.com/prosysscience/JSS

guokai-hh

comment created time in 3 months