# PyTorch Conference 2025 - Unsloth

我们的演讲包括： *在强化学习中最大化运气* 和 *强化学习能否导致通用人工智能？*

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

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

这是我们附上的 PDF 幻灯片：

{% file src="/files/c964f2a027647670ee2c1660323fcc779b84aaf5" %}

这是我们高质量 PNG 格式的幻灯片：

<div data-full-width="true"><figure><img src="/files/47d6edaca91bb3d7fa7a97fca742b4e80c705ac4" alt=""><figcaption></figcaption></figure> <figure><img src="/files/38d21c9894fb2e6989e90d06a63be4b8aef7669d" alt=""><figcaption></figcaption></figure> <figure><img src="/files/ae4c280885713ea41d9262a61a1f9a9cba82c913" alt=""><figcaption></figcaption></figure> <figure><img src="/files/2e259c60a5632a7d91c4a6ddf9e36c1bf363a2f1" alt=""><figcaption></figcaption></figure> <figure><img src="/files/767bfcde1d884f946ede309b44aca791077b2328" alt=""><figcaption></figcaption></figure> <figure><img src="/files/de5279ed2855dbd417dc85a1a5228c86a0b01283" alt=""><figcaption></figcaption></figure> <figure><img src="/files/f591c8439e42e117b3e41b989699caafb04b6963" alt=""><figcaption></figcaption></figure> <figure><img src="/files/0ab0b99db4e3182d4d90625c7179fe3d19022ea3" alt=""><figcaption></figcaption></figure> <figure><img src="/files/4068bd4665b518603c83d7f687b4fa5811c3b31f" alt=""><figcaption></figcaption></figure> <figure><img src="/files/2a0a3c2a87fd6e9edc225481af16f6f476bf2cc7" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/b5160cbf61308b8d55a5c1d3dbe516c1870e5b10" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b7231b0731a96d5573862a84fce7bfbe778af4be" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c8b2caf03e066ea60bf800f72b053e7ccadc664c" alt=""><figcaption></figcaption></figure> <figure><img src="/files/2b6b372bbc1879d59324a2813dd767a1441ee8a6" alt=""><figcaption></figcaption></figure> <figure><img src="/files/54f3cbe3ee3b5af901b7a8c7a65e9c89bfca93cc" alt=""><figcaption></figcaption></figure> <figure><img src="/files/198804648276d41ce4430bbdbd1ac05a0407bc9d" alt=""><figcaption></figcaption></figure> <figure><img src="/files/25bf215db25a4e021eb93768270414525e8695ba" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c50392b167cf61f370bffe416be56862e03ca5f5" alt=""><figcaption></figcaption></figure> <figure><img src="/files/f5c25acfdbebd368a8fb030e72dcbc719a816e97" alt=""><figcaption></figcaption></figure> <figure><img src="/files/0b043aef10d00e511acaf79dab6d4ea0b03c50d4" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/46b6d8f1d3ff37dc40ebda81d75d81fc61396417" alt=""><figcaption></figcaption></figure> <figure><img src="/files/518b185efe1fd6c9b8e50a99e62b639e8b508e3d" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b92e1d29af60148c9e4e54c580d45309a5004f28" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c81f6fa8b384986ccbc7f7eaacb1050487f731a9" alt=""><figcaption></figcaption></figure> <figure><img src="/files/29ce4504ddab91d415ccde8366b763861d1e2f01" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b46f8f470b91116e3b75e831a51037c9b2b45c46" alt=""><figcaption></figcaption></figure> <figure><img src="/files/ccb688b756f3e20b7095f34463a088b947170c18" alt=""><figcaption></figcaption></figure> <figure><img src="/files/7e81dc74d0fefe773b3a8ba961cebb83b6d8d378" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c7546a822c76f19ff4f71300f147753b62e75d69" alt=""><figcaption></figcaption></figure> <figure><img src="/files/6a5e42dfe549be2ca2d301575a4950de2038391c" alt=""><figcaption></figcaption></figure></div>

<div data-full-width="true"><figure><img src="/files/2921ac9c1a184bd5cfe5b950b8fea1c93fda950e" alt=""><figcaption></figcaption></figure> <figure><img src="/files/36a1c222e3e0b6901e05d10bb76bb81581f1ef26" alt=""><figcaption></figcaption></figure> <figure><img src="/files/c61cb4407e130fd6dbc0fe958555db2b443e58d1" alt=""><figcaption></figcaption></figure> <figure><img src="/files/98f9592481ac27110075693cf4e9266488611ab8" alt=""><figcaption></figcaption></figure> <figure><img src="/files/3e50cdb86a613b2eaf64b19e3ea7c696c6e46770" alt=""><figcaption></figcaption></figure> <figure><img src="/files/7304ee529a234782982af5711f7b2fb958b75041" alt=""><figcaption></figcaption></figure> <figure><img src="/files/b1bf4b339969e9b47a21a25807d42cdc7144f1a3" alt=""><figcaption></figcaption></figure> <figure><img src="/files/7215c4c2f7726e6bec79c61d1b2b9f680e5abaa5" alt=""><figcaption></figcaption></figure> <figure><img src="/files/4c9e450ac613f47d836b0324de50cfc3eadf793a" alt=""><figcaption></figcaption></figure> <figure><img src="/files/0143098cfbafce1b03dfe16577368bb7c70f4bc3" 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/zh/bo-ke/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.