Commit graph

85 commits

Author SHA1 Message Date
Earl Potters
ad21f178a1 Update choice history display in DynastAI prompt formatting
- Modified the prompt generation to include all choices made by the player instead of limiting to the last three.
- Enhanced the formatting to ensure clarity by stripping existing numbering from character prompts.
- Improved readability of the decision and effects displayed for each choice in the history.
2025-05-18 22:35:12 +00:00
Earl Potters
790e3848f5 Enhance DynastAI evaluation and prompt formatting with detailed debug logging
- Added debug print statements throughout the evaluation process to track the processing of test cards, input data, and generated prompts.
- Improved the `format_prompt` method to include detailed logging of kingdom state and choice history.
- Enhanced logging for training data selection to aid in debugging and understanding scenario generation.
2025-05-18 22:23:51 +00:00
Earl Potters
6f1a4f9a0b Merge branch 'main' into dynastai-reward-env 2025-05-18 21:59:52 +00:00
Earl Potters
7101aad190 Add DynastAI integration documentation and setup scripts
- Introduced `ATROPOS_INTEGRATION.md` for detailed instructions on using DynastAI with Atropos.
- Added `INSTALL_AND_RUN.md` to guide users through installation and running the game.
- Created `run_dynastai.py` for a simplified testing experience without full Atropos setup.
- Implemented `setup.py` to manage dependencies and ensure compatibility.
- Updated `requirements.txt` to include additional dependencies and version constraints.
- Enhanced `README.md` with new sections on installation, running the game, and integration with Atropos.
- Added installation verification script `verify_install.py` to check for required packages.
- Updated game logic to support local card generation and improved API integration.
- Enhanced web interface with new features for user interaction and game metrics display.
2025-05-18 21:59:12 +00:00
David van Vliet
38049522c8 formatting changes so that the game works 2025-05-18 14:52:32 -07:00
Earl Potters
b9a1940d12 Enhance evaluation process in DynastAI with detailed logging
- Added print statements to track the evaluation process, including the number of test scenarios and accuracy after evaluation.
- Improved JSON validation with additional logging for missing fields and invalid data types.
- Introduced counters for valid and invalid scenario generations during scoring.
- Enhanced feedback on scenario generation and processing errors for better debugging.
2025-05-18 21:23:33 +00:00
Earl Potters
fba2a42bb7 Enhance DynastAI scenario generation with structured point system and history tracking
- Updated point system guidelines to restrict values for Piety, Stability, Power, and Wealth to a range of -20 to 20.
- Introduced a category field for scenario classification.
- Added examples for scenario generation to improve clarity.
- Implemented choice history tracking to maintain a record of player decisions and their effects on the kingdom's state.
- Enhanced prompt formatting to include current kingdom state and recent choices for better context in scenario generation.
2025-05-18 21:13:13 +00:00
Earl Potters
e0dabe1225 Add DynastAI game environment with FastAPI backend and web frontend
- Introduced `dynastai_local_server.py` for local development and testing.
- Implemented `dynastai_server.py` as the main server entry point.
- Created FastAPI endpoints for game state management, card generation, and player choices.
- Developed a web interface with HTML, CSS, and JavaScript for user interaction.
- Added game logic for managing metrics and decision effects.
- Included configuration management and utility functions.
- Established a testing framework for API and environment functionality.
- Updated README.md with project overview and setup instructions.
2025-05-18 19:37:31 +00:00
Teknium
bdb15e5d85
Merge pull request #21 from NousResearch/add-sft-data-env
add an SFT data loading env
2025-05-17 11:30:07 -07:00
shannonsands
b1c9b23956
Merge pull request #50 from NousResearch/readme-updates
Added new env info
2025-05-17 10:22:20 -07:00
artem
651b40968d
Merge pull request #51 from NousResearch/kernelbench_env
Kernelbench env with parallel compilation
2025-05-16 21:38:57 -07:00
Artem Yatsenko
4b1c07232c readme updates 2025-05-17 04:37:09 +00:00
Artem Yatsenko
5396975bab move to its own folder, add readme, citation. 2025-05-17 04:34:49 +00:00
Shannon Sands
edf2beaa32 linting 2025-05-16 20:40:15 -07:00
Artem Yatsenko
9875f5dc06 pre-commit. add KB path as variable 2025-05-17 03:17:14 +00:00
Artem Yatsenko
fbfe06771b add parallel compile. add instructions 2025-05-16 19:53:46 -07:00
Shannon Sands
41caa05a1a remvoed merge error 2025-05-16 19:49:37 -07:00
Shannon Sands
9753d5a122 resolved conflict 2025-05-16 19:48:15 -07:00
Teknium
c9b6534eae
Merge pull request #44 from NousResearch/instruction-following-algo-environment
Instruction following algo environment
2025-05-16 19:37:00 -07:00
teknium1
20d263a495 add citation to allenai 2025-05-16 19:34:51 -07:00
teknium1
287bbcd356 some cleanup for final merge 2025-05-16 19:24:50 -07:00
Shannon Sands
fd63c76a5c Added new env info 2025-05-16 16:44:33 -07:00
teknium1
daa6f0ff18 add stricter enforcement of think tags 2025-05-16 13:18:20 -07:00
Artem Yatsenko
45aece515f first commit for kernelbench env 2025-05-16 11:29:10 -07:00
teknium1
6ae0703ad6 fix some regex and show special tokens for completions table 2025-05-15 22:29:42 -07:00
teknium1
24c571654e match num_max_requests with groupsize 2025-05-15 15:57:39 -07:00
Shannon Sands
bfb822f1e0 updated APIServerConfig and added requirements.txt and install instructions to README 2025-05-15 12:22:00 -07:00
hjc-puro
dcda88d79b fix validation errors 2025-05-15 04:30:59 -07:00
teknium1
1a9fa016b5 add dependencies to the env readme 2025-05-14 19:44:13 -07:00
teknium1
90e235a3e9 update environments readme 2025-05-14 19:40:32 -07:00
teknium1
2ab8905d4f fix score 2025-05-14 19:35:43 -07:00
teknium1
8a0e107806 change eval set size since this is a small dataset we need mo data for trainn 2025-05-14 19:18:01 -07:00
teknium1
bcc38567ca update some dataset stuff to use allenai's 2025-05-14 18:39:31 -07:00
teknium1
881af55f9a add instruction following algo env 2025-05-14 18:31:05 -07:00
Shannon Sands
c72a27d376 fixed linting in latest main 2025-05-14 17:29:57 -07:00
Shannon Sands
00dd120067 Merge branch 'main' into blackjack2-env 2025-05-14 17:27:44 -07:00
Shannon Sands
8fad665f6a moved folder location 2025-05-14 17:22:30 -07:00
Shannon Sands
c2bf3f5acd moved folder location 2025-05-14 17:22:18 -07:00
Joe Li
c1ae25c202
Merge pull request #26 from NousResearch/coding_server
add code execution environment
2025-05-14 15:08:10 -07:00
Shannon Sands
3fba8e3527 linting 2025-05-14 14:22:25 -07:00
Shannon Sands
d8ab1a6758 linting 2025-05-14 14:20:54 -07:00
Shannon Sands
1a7c0294fa refactoring for more clarity 2025-05-14 14:18:43 -07:00
Shannon Sands
bb6c205efe Linting 2025-05-14 14:05:52 -07:00
Shannon Sands
67cfd961c5 linting 2025-05-14 14:01:31 -07:00
Shannon Sands
826de9e283 Updated README 2025-05-14 13:57:20 -07:00
Shannon Sands
f5172b45a8 Added README 2025-05-14 13:35:15 -07:00
Shannon Sands
85f462df5e Updated test scripts 2025-05-14 12:05:59 -07:00
Shannon Sands
d6f9d58606 new env runs locally 2025-05-14 11:57:45 -07:00
Shannon Sands
54ae40840d no-thinking env added 2025-05-14 11:28:39 -07:00
Shannon Sands
21cc528b85 move best-of-n selection to util 2025-05-14 10:35:12 -07:00