From 2fe7ac0a71e37a887a7a90f86b1ac86bf4d5348b Mon Sep 17 00:00:00 2001 From: Simone Margaritelli Date: Mon, 14 Oct 2019 16:18:33 +0200 Subject: [PATCH] misc: small fix or general refactoring i did not bother commenting --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index f3a0d0f..cd3292d 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,6 @@ full and half WPA handshakes. ![alpha](https://media.giphy.com/media/f9GsXyfgEQbY65fnhu/source.gif) - Instead of merely playing [Super Mario or Atari games](https://becominghuman.ai/getting-mario-back-into-the-gym-setting-up-super-mario-bros-in-openais-gym-8e39a96c1e41?gi=c4b66c3d5ced) like most reinforcement learning-based "AI" *(yawn)*, Pwnagotchi tunes [its parameters](https://github.com/evilsocket/pwnagotchi/blob/master/pwnagotchi/defaults.yml#L73) over time to **get better at pwning WiFi things to** in the environments you expose it to. More specifically, Pwnagotchi is using an [LSTM with MLP feature extractor](https://stable-baselines.readthedocs.io/en/master/modules/policies.html#stable_baselines.common.policies.MlpLstmPolicy) as its policy network for the [A2C agent](https://stable-baselines.readthedocs.io/en/master/modules/a2c.html). If you're unfamiliar with A2C, here is [a very good introductory explanation](https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752) (in comic form!) of the basic principles behind how Pwnagotchi learns. (You can read more about how Pwnagotchi learns in the [Usage](https://www.pwnagotchi.ai/usage/#training-the-ai) doc.)