apprentissage_par_renforcement
Différences
Ci-dessous, les différences entre deux révisions de la page.
Les deux révisions précédentesRévision précédenteProchaine révision | Révision précédenteProchaine révisionLes deux révisions suivantes | ||
apprentissage_par_renforcement [2021/01/09 16:21] – [Baselines vs Stable-baselines vs Stable-baselines3] serge | apprentissage_par_renforcement [2021/01/09 17:36] – [Baselines vs Stable-baselines vs Stable-baselines3] serge | ||
---|---|---|---|
Ligne 76: | Ligne 76: | ||
* MushroomRL | * MushroomRL | ||
| | ||
- | ====Frameworks possibles==== | + | =====Frameworks possibles===== |
- | ===Gym de OpenAI=== | + | ====Gym de OpenAI==== |
+ | ===OpenAI=== | ||
* **[[https:// | * **[[https:// | ||
[[https:// | [[https:// | ||
- | | + | ===Gym=== |
- | * https:// | + | Gym is a toolkit for developing and comparing reinforcement learning algorithms. |
- | * http:// | + | |
+ | * [[https:// | ||
+ | * [[http:// | ||
- | ===Tensorforce=== | ||
- | * [[https:// | ||
- | sudo pip3 install tensorforce | ||
- | Successfully installed matplotlib-3.3.3 msgpack-1.0.2 msgpack-numpy-0.4.7.1 tensorboard-2.4.0 tensorflow-2.3.1 tensorflow-estimator-2.3.0 tensorforce-0.6.2 tqdm-4.55.0 | ||
====Baselines vs Stable-baselines vs Stable-baselines3==== | ====Baselines vs Stable-baselines vs Stable-baselines3==== | ||
Ligne 95: | Ligne 95: | ||
===Baselines=== | ===Baselines=== | ||
- | [[https:// | + | [[https:// |
===Stable-baselines=== | ===Stable-baselines=== |
apprentissage_par_renforcement.txt · Dernière modification : 2022/02/10 07:52 de serge