# linyilyi/street-fighter-ai

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/linyilyi-street-fighter-ai).**

6,527 stars · 1,394 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/linyiLYi/street-fighter-ai
- awesome-repositories: https://awesome-repositories.com/repository/linyilyi-street-fighter-ai.md

## Tags

### Artificial Intelligence & ML

- [Fighting Game Agent Training](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning/fighting-game-agent-training.md) — Trains an AI agent to play a fighting game by learning from raw pixel inputs via reinforcement learning.
- [Convolutional Feature Extractors](https://awesome-repositories.com/f/artificial-intelligence-ml/convolutional-feature-extractors.md) — Applies convolutional filters to raw pixel arrays for learning visual game patterns.
- [Convolutional Q-Network Implementations](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-q-learning-frameworks/convolutional-q-network-implementations.md) — Uses a convolutional neural network to approximate optimal action-value functions from raw pixels.
- [Experience Replay Buffers](https://awesome-repositories.com/f/artificial-intelligence-ml/experience-replay-buffers.md) — Stores past game transitions to break temporal correlations and stabilize training via random sampling.
- [Stochastic Exploration Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/exploration-strategies/stochastic-exploration-mechanisms.md) — Balances exploitation with random action selection using a decaying exploration rate schedule.
- [Agent Performance Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/reinforcement-learning-environments/reinforcement-learning-performance-visualizers/agent-performance-evaluators.md) — Evaluates trained agent win rates and generalization across training stages via automated testing. ([source](https://github.com/linyiLYi/street-fighter-ai#readme))
- [Sparse Reward Shapers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/objectives-and-optimization/mathematical-training-objectives/reward-functions/intrinsic-reward-mechanisms/sparse-reward-shapers.md) — Transforms sparse game outcomes into dense rewards by tracking health loss and damage dealt.
- [Pixel-Based Game](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-systems/training-frameworks/pixel-based-game.md) — Provides a framework for training game-playing agents using pixel observations and reinforcement learning.
- [Pixel-Based RL Training](https://awesome-repositories.com/f/artificial-intelligence-ml/pixel-based-rl-training.md) — Learns to play games by processing raw RGB pixel values from the screen without manual feature extraction.
- [Fighting Game Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning/fighting-game-agents.md) — Trains an AI agent via reinforcement learning that reads raw screen pixels to play a fighting game.
- [Pixel-Based Game Agent Training](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning/pixel-based-game-agent-training.md) — Trains an AI agent that reads raw screen pixels to learn and execute winning game actions. ([source](https://github.com/linyiLYi/street-fighter-ai/blob/master/.gitattributes))
- [Model Checkpointing](https://awesome-repositories.com/f/artificial-intelligence-ml/model-checkpointing.md) — Saves network weights at regular intervals to enable evaluation across training stages.

### Graphics & Multimedia

- [Frame Stacking Preprocessors](https://awesome-repositories.com/f/graphics-multimedia/frame-buffer-snapshots/sequential-frame-buffers/temporal-frame-interpolation/frame-stacking-preprocessors.md) — Combines consecutive game frames into a single state to capture motion and temporal dynamics.

### Part of an Awesome List

- [Fighting Game AI Evaluators](https://awesome-repositories.com/f/awesome-lists/ai/game-ai-environments/fighting-game-ai-evaluators.md) — Evaluates trained agent performance and win rates against a fighting game environment across training stages.