# PyTorch Conference 2025 - Unsloth

私たちの講演には以下が含まれます： *強化学習における運を最大化すること* および *強化学習は汎用人工知能（AGI）につながるか？*

{% columns %}
{% column %}
{% embed url="<https://www.youtube.com/watch?v=5ar9zi6VumI>" %}
{% endcolumn %}

{% column %}
{% embed url="<https://www.youtube.com/watch?v=2e7Q14RwEbc>" %}
{% endcolumn %}
{% endcolumns %}

こちらが添付のPDFスライドです：

{% file src="/files/3509a724413e2a4fa89fc405b73ce3cd479348ee" %}

こちらは高解像度PNG形式のスライドです：

<div data-full-width="true"><figure><img src="/files/26553dda7c076ecbe55a23926ff8f5740daedba6" alt=""><figcaption></figcaption></figure> <figure><img src="/files/803877b180cf9a0b404bbcde7ab262f069cebcba" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b45114cc954361d396674a4b3b7b648ae426388c" alt=""><figcaption></figcaption></figure> <figure><img src="/files/6d11648b8669a210640be3bf4459de6c9b347f3b" alt=""><figcaption></figcaption></figure> <figure><img src="/files/729f9ad638cc3f39f3bb319a403896eaff6762f0" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b3ce7693f51318fee43f8a9c554d5806069cd615" alt=""><figcaption></figcaption></figure> <figure><img src="/files/fb632e574087664db16ee2b30e95aa8344507ddb" alt=""><figcaption></figcaption></figure> <figure><img src="/files/2393520308e029223b4a2193fbac2b7913923387" alt=""><figcaption></figcaption></figure> <figure><img src="/files/eef93b9bb957279707d0ebe0fb6a3cc4b0eaa000" alt=""><figcaption></figcaption></figure> <figure><img src="/files/9caee2e07f33cd486911440256109c54cd63e1b2" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/53c18a6b3d197e318ea884764b44658ee11e296d" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c73e633d4249d15ba3d0ed17b10c758b52bbf935" alt=""><figcaption></figcaption></figure> <figure><img src="/files/abe2c7770158ef5f0754758fbe0d5731617d0774" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c69a440bbc5e97d0a25edb9cc083339e1f251bac" alt=""><figcaption></figcaption></figure> <figure><img src="/files/9894154be0ede9123488025c44d710adf4a45072" alt=""><figcaption></figcaption></figure> <figure><img src="/files/5f08e478b78d53b64429408dbe8d4f75b9db521f" alt=""><figcaption></figcaption></figure> <figure><img src="/files/48598df3ba98ba1a02a488a94a309368da1bfd38" alt=""><figcaption></figcaption></figure> <figure><img src="/files/f1bdf67e0e63beb7bd8a60c8a57fb71002abff8f" alt=""><figcaption></figcaption></figure> <figure><img src="/files/3ce0284c412cc3165dad6a7431022493e18a56be" alt=""><figcaption></figcaption></figure> <figure><img src="/files/8f3da932afbb2b56452983d34a5bf4f64fb535ad" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/3f9ae94aa21ef455fc8b8463a2137880ccc9b7fb" alt=""><figcaption></figcaption></figure> <figure><img src="/files/8d28f5d6f692a2cab3c3376ad0a1de7ba9da037d" alt=""><figcaption></figcaption></figure> <figure><img src="/files/8508547b239ccb8b00dde3495d430567af7f740e" alt=""><figcaption></figcaption></figure> <figure><img src="/files/46fb636384e4ba2f54bfd1764af961ad5616d937" alt=""><figcaption></figcaption></figure> <figure><img src="/files/f79009055a3c0b6c2f6018e0f709817693a48426" alt=""><figcaption></figcaption></figure> <figure><img src="/files/a96bef38f6fb975c3bae4e97c5a269d0360020dd" alt=""><figcaption></figcaption></figure> <figure><img src="/files/398562d44c492d865ae71ffcb79f0a89c42757c5" alt=""><figcaption></figcaption></figure> <figure><img src="/files/da84fd5f75a2320c6157881426515fe0ce7ffffb" alt=""><figcaption></figcaption></figure> <figure><img src="/files/d45850a59bb651f195d9d7197493eab5da4f9c52" alt=""><figcaption></figcaption></figure> <figure><img src="/files/7cc06df478186ec1abfce6bbf66af0704e92f7f0" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/5daa55fd6612a11674feeb081fc2c3d413aaf056" alt=""><figcaption></figcaption></figure> <figure><img src="/files/9161f3434ad8138d13d00db95c91a9e877c11bb6" alt=""><figcaption></figcaption></figure> <figure><img src="/files/798ae8e530a84438277ca0bf4ec129ad18912a6e" alt=""><figcaption></figcaption></figure> <figure><img src="/files/d22101c1ea7b191201e14266fbb5b50527d4ff8b" alt=""><figcaption></figcaption></figure> <figure><img src="/files/1014c1c7e9b54f51e0f22139ab3bf2dae632d656" alt=""><figcaption></figcaption></figure> <figure><img src="/files/56132de53f22a1157676f58a72a4c6581e873084" alt=""><figcaption></figcaption></figure> <figure><img src="/files/8cb92c29b0f6987e82a5735c1e7b1d058d6f459f" alt=""><figcaption></figcaption></figure> <figure><img src="/files/e9af0007d00c3bfdb1fe7fab87a589ad464f7c9e" alt=""><figcaption></figcaption></figure> <figure><img src="/files/fe915b8f92e8a249558e88c7d8f4da78ce15cf6f" alt=""><figcaption></figcaption></figure> <figure><img src="/files/1152a57060a991cbe8837dfd247265d8c7ce3133" alt=""><figcaption></figcaption></figure></div>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/jp/burogu/pytorch-conference-2025-unsloth.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.