# DOOM Neuron

## Docs

- [DOOM Neuron - Train Biological Neurons to Play DOOM](https://mintlify.wiki/SeanCole02/doom-neuron/introduction.md): Train biological neurons using reinforcement learning to play DOOM. Combines CL1 hardware with PPO to create adaptive neural controllers.
- [Quickstart](https://mintlify.wiki/SeanCole02/doom-neuron/quickstart.md): Get DOOM Neuron training running in minutes with real biological neurons
- [Installation](https://mintlify.wiki/SeanCole02/doom-neuron/installation.md): Install DOOM Neuron dependencies including VizDoom, CL SDK, PyTorch, and configure your training environment
- [System Architecture](https://mintlify.wiki/SeanCole02/doom-neuron/concepts/architecture.md): Distributed architecture for training biological neurons to play DOOM using PPO reinforcement learning
- [PPO Training](https://mintlify.wiki/SeanCole02/doom-neuron/concepts/ppo-training.md): How Proximal Policy Optimization trains biological neurons to play DOOM using policy gradients, GAE, and reward shaping
- [Neural Interface](https://mintlify.wiki/SeanCole02/doom-neuron/concepts/neural-interface.md): How the CL1 biological neural hardware receives stimulation and generates spike responses for DOOM gameplay
- [Feedback System](https://mintlify.wiki/SeanCole02/doom-neuron/concepts/feedback-system.md): How surprise-scaled feedback mechanisms provide additional learning signals through dedicated reward channels
- [Local Setup](https://mintlify.wiki/SeanCole02/doom-neuron/guides/local-setup.md): Setting up DOOM Neuron for local development and testing on a single machine
- [Remote Training](https://mintlify.wiki/SeanCole02/doom-neuron/guides/remote-training.md): Setting up DOOM Neuron for remote training with CL1 hardware on a separate device
- [DOOM Scenarios](https://mintlify.wiki/SeanCole02/doom-neuron/guides/scenarios.md): Available DOOM scenarios and curriculum stages for training biological neurons
- [Checkpoint Management](https://mintlify.wiki/SeanCole02/doom-neuron/guides/checkpoint-management.md): Saving, loading, and resuming training with model checkpoints in DOOM Neuron
- [PPO Configuration](https://mintlify.wiki/SeanCole02/doom-neuron/configuration/ppo-config.md): Complete reference for PPOConfig parameters including learning rate, gamma, GAE, entropy coefficients, and batch size settings for PPO reinforcement learning
- [Encoder & Decoder Architecture](https://mintlify.wiki/SeanCole02/doom-neuron/configuration/encoder-decoder.md): Configuration reference for encoder and decoder neural networks including CNN options, MLP options, weight constraints, and trainability settings
- [Action Space Configuration](https://mintlify.wiki/SeanCole02/doom-neuron/configuration/action-spaces.md): Configure hybrid vs discrete action spaces, movement controls, camera turning, and attack actions for biological neural control
- [Feedback Tuning](https://mintlify.wiki/SeanCole02/doom-neuron/configuration/feedback-tuning.md): Configure feedback stimulation parameters including amplitude, frequency, pulse count, and surprise-based scaling for event-driven neural feedback
- [Ablation Modes](https://mintlify.wiki/SeanCole02/doom-neuron/advanced/ablations.md): Validate neural contributions by comparing real CL1 spikes against zero and random controls
- [Curriculum Learning](https://mintlify.wiki/SeanCole02/doom-neuron/advanced/curriculum-learning.md): Progressive difficulty training with the deadly corridor curriculum (levels 1-5)
- [Troubleshooting](https://mintlify.wiki/SeanCole02/doom-neuron/advanced/troubleshooting.md): Common issues, debugging tips, and TensorBoard monitoring for DOOM Neuron training
- [ppo_doom.py](https://mintlify.wiki/SeanCole02/doom-neuron/api/ppo-doom.md): PPO reinforcement learning script for training biological neurons to play DOOM using CL1 hardware interface
- [training_server.py](https://mintlify.wiki/SeanCole02/doom-neuron/api/training-server.md): Remote training server that communicates with CL1 hardware over UDP for distributed neural training
- [cl1_neural_interface.py](https://mintlify.wiki/SeanCole02/doom-neuron/api/cl1-interface.md): Hardware interface server that runs on CL1 device to manage neural stimulation and spike recording
- [udp_protocol.py](https://mintlify.wiki/SeanCole02/doom-neuron/api/udp-protocol.md): UDP packet formats and utilities for real-time communication between training system and CL1 device
- [PPOConfig Reference](https://mintlify.wiki/SeanCole02/doom-neuron/api/config-reference.md): Complete configuration dataclass for PPO training and neural interface parameters in DOOM Neuron
- [EventFeedbackConfig Reference](https://mintlify.wiki/SeanCole02/doom-neuron/api/event-feedback.md): Configuration dataclass for event-based feedback stimulation with temporal difference (TD) error scaling