| ---
|
| license: apache-2.0
|
| library_name: pytorch
|
| tags:
|
| - decision-making
|
| - pacman
|
| - knowledge-distillation
|
| - tabular-classification
|
| datasets:
|
| - guilindev/pacman-decision-oracle-v1
|
| ---
|
|
|
| # Pac-Man Decision Tiny · 17,601 parameters
|
|
|
| A small, newly trained PyTorch policy that chooses among legal Pac-Man directions.
|
| It learns from a five-second simulation/search teacher and runs locally on CPU.
|
| **The safe tensor weight file is about 72 KB.**
|
|
|
| **[Interactive experiment explorer](https://huggingface.co/spaces/guilindev/pacman-decision-lab)** ·
|
| **[Training data](https://huggingface.co/datasets/guilindev/pacman-decision-oracle-v1)** ·
|
| **[Qwen LoRA comparison](https://huggingface.co/guilindev/pacman-decision-qwen3-0.6b)**
|
|
|
| ## What the first experiment found
|
|
|
| Same 4,096 training examples and 512 validation examples for both learned policies:
|
|
|
| | Policy | Validation top-choice agreement with search teacher |
|
| |---|---:|
|
| | Original Qwen3-0.6B, option-token scoring | 25.39% |
|
| | Qwen3-0.6B, one-epoch LoRA pilot | 32.23% |
|
| | Uniform random legal choice (expected) | 31.67% |
|
| | Always first listed option | 38.87% |
|
| | **This structured policy** | **50.20%** |
|
|
|
| The Qwen pilot remains near chance and its 32 inspected decisions always selected
|
| the second option. This tiny baseline was added after that diagnosis, before its
|
| own gameplay test. It is a separate supervised model trained from scratch, not a
|
| Qwen adapter, a Jev model, or a multimodal model.
|
|
|
| ### Independent gameplay pilot
|
|
|
| Three held-out seeds (100, 101, 102), one fixed maze, speed 1, realtime clock,
|
| 180 simulated seconds maximum per game. Actual request latency advances the game.
|
| Training was stopped during inference. All tests ran on the same DGX host;
|
| the tiny policy runs on CPU, while Qwen runs on the GPU.
|
|
|
| | Policy | Mean pellets / game | Mean per-game request p50 |
|
| |---|---:|---:|
|
| | base | 0.0 | 21 ms |
|
| | greedy | 173.3 | 0 ms |
|
| | random | 33.0 | 0 ms |
|
| | structured | 304.3 | 1 ms |
|
| | trained | 49.0 | 21 ms |
|
|
|
| Zero ms denotes integer-ms reporting resolution, not zero computation.
|
|
|
| Every per-seed score is in `gameplay_results.json`. This is a three-game exploratory
|
| comparison, not a claim about unseen maps or games. The tiny policy was selected
|
| using validation cross-entropy, never gameplay test scores. Jev was not measured.
|
|
|
| ## Architecture and training
|
|
|
| Each legal option is encoded by 15 numeric facts: current lives, remaining pellets,
|
| distance to junction, frightened time, ghost distances and presence, approaching
|
| ghost flag, edible-ghost distance, nearby food, power-pellet distance, and whether
|
| the option means turning back. Feature scales are fixed constants in the source.
|
|
|
| A shared 15 → 64 → 64 option network is followed by mean/max set pooling and a
|
| 192 → 64 → 1 scoring network. Softmax is restricted to legal choices. Shared weights
|
| and set pooling make it permutation-equivariant: reordering options reorders the
|
| scores. The measured permutation check differed by at most 2.1e-07.
|
|
|
| Training: NVIDIA GB10, FP32, seed 42, AdamW 0.001, weight decay 0.0001, batch 128,
|
| 100 epochs. Check validation every 10 epochs; epoch 90 has the lowest
|
| cross-entropy (1.0931) and is released. Training plus validation took
|
| 8.6 seconds, excluding data generation and model setup.
|
|
|
| The label is a soft distribution over a search oracle's values (temperature 50).
|
| No future state or oracle score is supplied at inference. See the data card for
|
| the collection recipe, seed ranges, duplicate removal and exact file hashes.
|
|
|
| ## Run it on your computer
|
|
|
| Download `structured_policy.py`, `predict_tiny.py`, and `example.json` from this repo,
|
| then run:
|
|
|
| ```bash
|
| pip install torch safetensors huggingface_hub
|
| python predict_tiny.py --request example.json
|
| ```
|
|
|
| The script downloads this repository's tiny weight file and prints a legal direction
|
| and candidate distribution. It executes on CPU. The model uses custom PyTorch code;
|
| it is not an `AutoModelForCausalLM` checkpoint.
|
|
|
| To reproduce training on a CUDA GPU:
|
|
|
| ```bash
|
| python download_data.py
|
| python train_structured.py
|
| ```
|
|
|
| ## Scope and attribution
|
|
|
| The policy uses structured text-derived game facts, not pixels. It has not been
|
| trained or evaluated for general language reasoning, real-world inspection or
|
| multimodal perception. Candidate scores are relative preferences, not calibrated
|
| probabilities of survival. Three seeds are a small pilot; wider evaluation remains
|
| necessary before drawing a general performance conclusion.
|
|
|
| Game engine, feature encoder and search oracle: [grapeot/decision-pacman](https://github.com/grapeot/decision-pacman),
|
| commit `593ed1f59f4f97ad0bda7287ff304e9667360089`, MIT (`LICENSE.upstream`).
|
| This project supplies the fresh data collection, shared-option policy architecture,
|
| new GPU training run and artifacts. Weights are Apache-2.0. Personal research project.
|
|
|
