Downloads · 30 days
0
gol-grpo-diversified-37991023
brysgo/gol-grpo-diversified-37991023
gol-grpo-diversified-37991023 is a reinforcement learning model from brysgo. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
Repository: brysgo/gol-grpo-diversified-37991023
Access
Public
Updated May 27, 2026
Repo size
3.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4 GB · 71%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- May 27, 2026
- Updated
- May 27, 2026
- SHA
- 220eced4
Model card
From the Hugging Face model README
GoL RL Run Artifacts
Repository: brysgo/gol-grpo-diversified-37991023
This repo contains artifacts from a Conway's Game of Life agentic RL run.
Contents
grpo_training_data.jsonl: prompt, thought, action, reward, and observed state trajectories.rl_trajectories_with_cot.jsonl: environment-side trajectory log with chain-of-thought separated from action JSON.logs/collection_summary.json: aggregate data-collection metrics.logs/grpo_reward_100_fixed.jsonl: reward log from the 100-step GRPO run.logs/train_grpo_100_fixed.log: training log for the completed fixed GRPO run.gol-grpo-100-fixed/: trainer metadata/config. Large model weights are included only when uploaded with--include-modeland present locally.
Collection Summary
- Total episodes:
unknown - Reward min:
unknown - Reward max:
unknown - Reward mean:
unknown - Empty thoughts:
unknown - Format failures:
unknown
Caveats
The first 100-step GRPO run completed, but generated completions were clipped at the configured maximum length. Later local code changes tightened prompt formatting, added format penalties, and hardened reward logic against detector/entity-count exploits.
- Task
- Reinforcement Learning
- Library
- transformers
- License
- mit
- Created
- May 27, 2026
- Updated
- May 27, 2026