Agent Demo List · opendilab/DI-engine

(6 commenti) (2 reazioni) (0 assegnatari)Python (437 fork)github user discovery

discussiongood first issue

Metriche repository

Star: (3639 stelle)
Metriche merge PR: (Nessuna PR mergiata in 30 g)

Descrizione

This issue is a collection of various interesting agent demonstration trained by DI-engine, it will be updated continually.

Mario 1-1

https://user-images.githubusercontent.com/33195032/184529481-f55642f7-e9e8-45d3-9b8c-80e5bf3e177b.mp4
Mario 1-2

https://user-images.githubusercontent.com/33195032/184669648-6309ba32-4d33-4b07-8ce0-cce89c82bf97.mp4
rocket landing

https://user-images.githubusercontent.com/33195032/204750411-2c3c4fb3-de6c-474a-a4d3-dd380a605de1.mp4
SMAC 5m VS 6m

https://user-images.githubusercontent.com/33195032/125911080-2fdbd8ce-1107-455b-9772-eac20b717dab.mp4
SMAC MMM

https://user-images.githubusercontent.com/33195032/125910360-de914769-f0fc-4073-85a7-b12b1ef32fa7.mp4
SMAC MMM2

https://user-images.githubusercontent.com/33195032/126481161-9127f790-bfca-4985-bed3-7adaab519b46.mp4
SMAC 3s5z

https://user-images.githubusercontent.com/33195032/125908605-d694bb6a-b10a-4b58-9ec2-b4eb92cfe7a3.mp4
lunarlander

https://user-images.githubusercontent.com/33195032/127827210-cbc1e23c-6ed4-4d5b-a3c4-34a010119993.mp4
gfootball
- rule-based bot vs rule-based bot
https://user-images.githubusercontent.com/33195032/125933672-db8a6229-c2ea-4ab6-a53e-355a2258a0f3.mp4
- trained agent vs rule-based bot
https://user-images.githubusercontent.com/33195032/125933646-e24df3ec-9ec3-41d7-a693-136331f6a27a.mp4
slime_volley
- rule-base bot vs trained agent

Guida contributor

Direzione di ricerca: Registra un video di un agente addestrato che gioca in un nuovo ambiente e aggiungilo alla lista. Guarda gli esempi esistenti per il formato.
Tech stack: python
Dominio: machine learningai
Tipo issue: Ricerca
Difficoltà: 1
Tempo stimato: Meno di 1 ora
Stato attività: Attiva
Chiarezza: Chiara
Prerequisiti: PythonReinforcement learning
Adatta ai principianti: 90