# Announcements

## Latest Updates

### 06.07

The leaderboard has been updated and it's now in the test phase! 

### 05.07

* We have now uploaded the **test instances** for tracks 1 and 2. Please merge the recent changes from Github to get the updates. :arrow\_down: 
* For track 1 (Surrogate) the **test seed is 6537855 -** it can be found in `check_solution_surrogate.py`
* For track 2 (RL) the test seed for all instances is **19120623** :calendar: - it can be found in `baseline_rl/example_output_rl.py`, `env_rl.py` and `check_solution_rl.py`
* The **instance files** for track 2's test phase can be found in the folder `data/test`
* As in the validation phase, the **test phase of track 2** requires **100 Monte Carlo samples for each instance.** :game\_die: 
* The validation phase is still running so we have not changed the submission system yet. We will do so when the validation phase is over. 
* The leaderboard will be reset for the test phase. Please make sure you **submit your solutions again** on the website when the **test phase leaderboard is active.** :arrow\_up: 

### 28.06

* We are **one week** away from the end of the validation phase (**05.07**).
* After the validation phase is over we will provide the *test instances* on the [Github](https://github.com/paulorocosta/ai-for-tsp-competition) repository. 
* You will have again **one week** to submit your results for the test instances (**12.07 - AoE**). 
* Winners will be selected based on the **results of the test phase**. 
* If you have any technical problems with your submission during the test phase, please let us know as soon as possible so we can find a workaround for your case.
* If possible, please submit your test results **before the deadline** to avoid any issues near the end of the deadline.
* Best of luck! :shamrock: 

### 28.05

* Prizes have been announced! Please check [here](https://paulorocosta.gitbook.io/ai4tsp-competition/master#prizes).

### 27.05

* 🎉 We are sorry about the delay but happy to announce that we are now officially in the **validation phase!** 👊🏻
* The validation instance of Track 1 has been updated. :rocket: 
* The validation instances of Track 2 remain the same as the tryout phase. :robot: 
* Because we want to look fancier we are also introducing our Documentation page.![:dancer:](https://a.slack-edge.com/production-standard-emoji-assets/13.0/google-medium/1f483.png)
* Within the documentation page, you can find our [FAQ](https://paulorocosta.gitbook.io/ai4tsp-competition/faq), [README](https://paulorocosta.gitbook.io/ai4tsp-competition/readme) and [Announcements](https://paulorocosta.gitbook.io/ai4tsp-competition/announcements).
* We thank all participants that helped us improve the competition in the tryout phase.![:muscle:](https://a.slack-edge.com/production-standard-emoji-assets/13.0/google-medium/1f4aa.png)

### 14.05

* We have updated `batch_env_rl.py` to read from files appropriately. :arrow\_up\_small: 
* We have fixed a bug in the noisy travel times introduced in the last update. :lady\_beetle: 

### 11.05

* We are now in the tryout phase. This phase runs until the ~~**21st of May**~~**  27th of May**. Please expect a few updates to the master code until then. After this date, no further changes will be introduced. 
* We kindly ask you to report any issues you may encounter via the issues page on the Github repo or via the slack channel. 
* We changed the way randomness is calculated in the environments. Please update your code. 


---

# 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://paulorocosta.gitbook.io/ai4tsp-competition/announcements.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.