aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-02-23 07:04:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

Move Auto-GPT to autogpts/autogpt

Browse Source
This commit is contained in:
Merwane Hamadi
2023-09-05 09:40:24 -07:00
parent ba030eac1d
commit 8489052358
324 changed files with 472 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
docs/challenges/memory/challenge_a.md
View File

@@ -1,39 +0,0 @@
# Memory Challenge A
**Status**: Challenge Completed
## Description
The agent, Follow-Instructions-GPT, has the following goals:
- Use the command `read_file` to read the `instructions_1.txt` file.
- Follow the instructions in the `instructions_1.txt` file.
The challenge involves a series of text files containing instructions. The agent must follow the instructions and keep track of the task ID as it progresses through the files.
## Files
- `instructions_1.txt`
The task_id is 1234
Read the file instructions_1.txt
- `instructions_2.txt`
Read the file instructions_2.txt using the read_file command.
...and so on.
- `instructions_n.txt`
Write the task_id into the file output.txt.
## Objective
The objective of this challenge is to test the agent's ability to follow instructions and maintain memory of the task Id throughout the process. The agent successfully completed this challenge if it wrote the task id in a file.

44
docs/challenges/memory/challenge_b.md
View File

@@ -1,44 +0,0 @@
# Memory Challenge B
**Status**: Current level to beat: level 3
**Command to try**:
```shell
pytest -s tests/challenges/memory/test_memory_challenge_b.py --level=3
```
## Description
The agent, Follow-Instructions-GPT, has the following goals:
- Use the command `read_file` to read the `instructions_1.txt` file.
- Follow the instructions in the `instructions_1.txt` file.
The challenge involves a series of text files containing instructions and task IDs. The agent must follow the instructions and keep track of the task IDs as it progresses through the files.
## Files
- `instructions_1.txt`
The current task_id is 4563.\n[NOISE intended to confuse the agent]
Read the file instructions_2.txt using the read_file command.
- `instructions_2.txt`
The current task_id is 6182.\n[NOISE intended to confuse the agent]
Read the file instructions_3.txt using the read_file command.
...and so on.
- `instructions_n.txt`
The current task_id is 8912.
Write all the task_ids into the file output.txt. The file has not been created yet. After that, use the task_complete command.
## Objective
The objective of this challenge is to test the agent's ability to follow instructions and maintain memory of the task IDs throughout the process. The agent successfully completed this challenge if it wrote the task ids in a file.

61
docs/challenges/memory/challenge_c.md
View File

@@ -1,61 +0,0 @@
# Memory Challenge C
**Status**: Current level to beat: level 1
**Command to try**:
```shell
pytest -s tests/challenges/memory/test_memory_challenge_c.py --level=2
```
## Description
The agent, Follow-Instructions-GPT, has the following goals:
- Use the command `read_file` to read the `instructions_1.txt` file.
- Follow the instructions in the `instructions_1.txt` file.
The challenge involves a series of text files containing instructions and silly phrases. The agent must follow the instructions and keep track of the task IDs as it progresses through the files.
## Files
- `instructions_1.txt`
The current phrase is
```
The purple elephant danced on a rainbow while eating a taco.\n[NOISE intended to confuse the agent]
```
Read the file `instructions_2.txt` using the read_file command.
- `instructions_2.txt`
The current phrase is
```
The sneaky toaster stole my socks and ran away to Hawaii.\n[NOISE intended to confuse the agent]
```
Read the file instructions_3.txt using the read_file command.
...and so on.
- `instructions_n.txt`
The current phrase is
```
My pet rock sings better than Beyoncé on Tuesdays.
```
Write all the phrases into the file output.txt. The file has not been created yet. After that, use the task_complete command.
## Objective
The objective of this challenge is to test the agent's ability to follow instructions and maintain memory of the task IDs throughout the process. The agent successfully completed this challenge if it wrote the phrases in a file.
This is presumably harder than task ids as the phrases are longer and more likely to be compressed as the agent does more work.

80
docs/challenges/memory/challenge_d.md
View File

@@ -1,80 +0,0 @@
# Memory Challenge D
**Status**: Current level to beat: level 1
**Command to try**:
```shell
pytest -s tests/challenges/memory/test_memory_challenge_d.py --level=1
```
## Description
The provided code is a unit test designed to validate an AI's ability to track events and beliefs of characters in a story involving moving objects, specifically marbles. This scenario is an advanced form of the classic "Sally-Anne test", a psychological test used to measure a child's social cognitive ability to understand that others' perspectives and beliefs may differ from their own.
Here is an explanation of the challenge:
The AI is given a series of events involving characters Sally, Anne, Bob, and Charlie, and the movements of different marbles. These events are designed as tests at increasing levels of complexity.
For each level, the AI is expected to keep track of the events and the resulting beliefs of each character about the locations of each marble. These beliefs are affected by whether the character was inside or outside the room when events occurred, as characters inside the room are aware of the actions, while characters outside the room aren't.
After the AI processes the events and generates the beliefs of each character, it writes these beliefs to an output file in JSON format.
The check_beliefs function then checks the AI's beliefs against the expected beliefs for that level. The expected beliefs are predefined and represent the correct interpretation of the events for each level.
If the AI's beliefs match the expected beliefs, it means the AI has correctly interpreted the events and the perspectives of each character. This would indicate that the AI has passed the test for that level.
The test runs for levels up to the maximum level that the AI has successfully beaten, or up to a user-selected level.
## Files
- `instructions_1.txt`
```
Sally has a marble (marble A) and she puts it in her basket (basket S), then leaves the room. Anne moves marble A from Sally's basket (basket S) to her own basket (basket A).
```
- `instructions_2.txt`
```
Sally gives a new marble (marble B) to Bob who is outside with her. Bob goes into the room and places marble B into Anne's basket (basket A). Anne tells Bob to tell Sally that he lost the marble b. Bob leaves the room and speaks to Sally about the marble B. Meanwhile, after Bob left the room, Anne moves marble A into the green box, but tells Charlie to tell Sally that marble A is under the sofa. Charlie leaves the room and speak to Sally about the marble A as instructed by Anne.
```
...and so on.
- `instructions_n.txt`
The expected believes of every characters are given in a list:
```json
expected_beliefs = {
1: {
'Sally': {
'marble A': 'basket S',
},
'Anne': {
'marble A': 'basket A',
}
},
2: {
'Sally': {
'marble A': 'sofa', # Because Charlie told her
},
'Anne': {
'marble A': 'green box', # Because she moved it there
'marble B': 'basket A', # Because Bob put it there and she was in the room
},
'Bob': {
'B': 'basket A', # Last place he put it
},
'Charlie': {
'A': 'sofa', # Because Anne told him to tell Sally so
}
},...
```
## Objective
This test essentially checks if an AI can accurately model and track the beliefs of different characters based on their knowledge of events, which is a critical aspect of understanding and generating human-like narratives. This ability would be beneficial for tasks such as writing stories, dialogue systems, and more.

5
docs/challenges/memory/introduction.md
View File

@@ -1,5 +0,0 @@
# Memory Challenges
Memory challenges are designed to test the ability of an AI agent, like Auto-GPT, to remember and use information throughout a series of tasks. These challenges often involve following instructions, processing text files, and keeping track of important data.
The goal of memory challenges is to improve an agent's performance in tasks that require remembering and using information over time. By addressing these challenges, we can enhance Auto-GPT's capabilities and make it more useful in real-world applications.