What does pwhiddy/pokemonredexperiments do?

This project is a game AI training framework designed to develop and monitor reinforcement learning agents within a legacy game environment. It functions as a training and monitoring system that optimizes autonomous agents to complete game objectives through exploration and reward-based learning.

What are the main features of pwhiddy/pokemonredexperiments?

The main features of pwhiddy/pokemonredexperiments are: Agentic Training Frameworks, Reinforcement Learning, State-Action-Reward Interfaces, Game AI, Game-Based, Training Monitoring Tools, Reinforcement Learning Training, Game Memory Coordinate Mappings.

Which projects share features with pwhiddy/pokemonredexperiments?

Projects with overlapping indexed features include: openpipe/art — ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and… aws/amazon-sagemaker-examples — This repository is a collection of Jupyter notebooks providing reference implementations and templates for building,… nyandwi/machine_learning_complete — This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep… tensorflow/minigo — Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a… zhaochenyang20/awesome-ml-sys-tutorial — This project provides a comprehensive technical guide and framework for engineering large-scale machine learning… xbpeng/deepmimic — DeepMimic is a deep reinforcement learning framework and physics-based motion imitation tool designed to teach…

PokemonRedExperiments - train AI agents

Name: pwhiddy/pokemonredexperiments
Author: PWhiddy

Features

Agentic Training Frameworks - Provides a comprehensive framework for training autonomous agents to achieve objectives via environment feedback and trajectory optimization.
Reinforcement Learning - Provides a framework for training agents to complete game objectives through trial-and-error reinforcement learning.
State-Action-Reward Interfaces - Coordinates the exchange of game states, actions, and rewards to refine navigation policies.
Game AI - Develops intelligent agents capable of completing tasks within a legacy game engine.
Game-Based - Implements an autonomous agent trained to complete game objectives via reward optimization in a legacy game environment.
Training Monitoring Tools - Provides tools for logging performance metrics and analyzing decision-making during reinforcement learning.
Reinforcement Learning Training - Trains autonomous agents to complete game objectives by optimizing exploration and goal progression.
Game Memory Coordinate Mappings - Translates raw game memory addresses into a visual coordinate system to plot agent movement patterns.
Memory Mapping Utilities - Reads raw game memory addresses directly to derive entity positions and environmental data.
Game Memory Extraction - Accesses game memory directly to extract entity positions and environmental data for the agent.
Memory Address Mapping - Implements a system to translate raw game memory addresses into visual coordinates for tracking entity positions.
Game Memory State Monitoring - Extracts and logs raw memory data from a running game to track agent performance.
Agent Trajectory Logs - Records and inspects agent trajectories and performance metrics on an external dashboard for analysis.
Behavioral Analysis - Tracks movement patterns and decision-making processes to analyze how AI navigates virtual environments.
Training Progress Monitoring - Streams real-time session data to a global map to visualize movement and area exploration.
Training Progress Monitors - Ships a dashboard for tracking real-time metrics and session data during the agent training process.
Agent Trajectory Visualizations - Streams real-time agent session data to a map to visualize navigation patterns and area exploration.
Real-Time Map Visualizations - Streams movement data to a map to monitor AI navigation and exploration in real time.
Agent Performance Visualizers - Renders agent movements and positions on a map in real-time to analyze navigation patterns.
Model Training Metrics - Logs performance data to external dashboards to monitor training progress and agent behavior.
Real-Time Metric Visualization - Streams live session data to global maps and dashboards to monitor learning progress.

Projects sharing features with PokemonRedExperiments

These projects share indexed features with PokemonRedExperiments. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.

openpipe/art
OpenPipe/ART
8,630View on GitHub
ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin
Pythonagentagentic-aigrpo
View on GitHub8,630
aws/amazon-sagemaker-examples
aws/amazon-sagemaker-examples
10,958View on GitHub
This repository is a collection of Jupyter notebooks providing reference implementations and templates for building, training, and deploying machine learning models using Amazon SageMaker. It serves as an example library for implementing model architectures and automating the machine learning lifecycle. The library provides practical patterns for machine learning training, data engineering, and model deployment. It includes implementation guides for MLOps, including workflows for model monitoring, lineage tracking, and hyperparameter tuning. The examples cover a broad range of capabilities i
Jupyter Notebookawsdata-sciencedeep-learning
View on GitHub10,958
nyandwi/machine_learning_complete
Nyandwi/machine_learning_complete
4,983View on GitHub
This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep learning and natural language processing. It uses real datasets and multiple frameworks within a structured, hands-on curriculum that combines concise explanations with executable code cells, built-in datasets, and embedded exercise checkpoints. Learning progresses through data preparation and exploration, classical machine learning workflows, computer vision with convolutional neural networks, and natural language processing with deep learning, all delivered as a cohesive progressi
Jupyter Notebookcomputer-visiondata-analysisdata-science
View on GitHub4,983
tensorflow/minigo
tensorflow/minigo
3,531View on GitHub
Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge
C++
View on GitHub3,531

Compare all 30 related projects

Projects sharing features with PokemonRedExperiments

These projects share indexed features with PokemonRedExperiments. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.

openpipe/art
OpenPipe/ART
8,630View on GitHub
ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin
Pythonagentagentic-aigrpo
View on GitHub8,630
aws/amazon-sagemaker-examples
aws/amazon-sagemaker-examples
10,958View on GitHub
This repository is a collection of Jupyter notebooks providing reference implementations and templates for building, training, and deploying machine learning models using Amazon SageMaker. It serves as an example library for implementing model architectures and automating the machine learning lifecycle. The library provides practical patterns for machine learning training, data engineering, and model deployment. It includes implementation guides for MLOps, including workflows for model monitoring, lineage tracking, and hyperparameter tuning. The examples cover a broad range of capabilities i
Jupyter Notebookawsdata-sciencedeep-learning
View on GitHub10,958
nyandwi/machine_learning_complete
Nyandwi/machine_learning_complete
4,983View on GitHub
This is an interactive notebook-based course that teaches machine learning from Python fundamentals through deep learning and natural language processing. It uses real datasets and multiple frameworks within a structured, hands-on curriculum that combines concise explanations with executable code cells, built-in datasets, and embedded exercise checkpoints. Learning progresses through data preparation and exploration, classical machine learning workflows, computer vision with convolutional neural networks, and natural language processing with deep learning, all delivered as a cohesive progressi
Jupyter Notebookcomputer-visiondata-analysisdata-science
View on GitHub4,983
tensorflow/minigo
tensorflow/minigo
3,531View on GitHub
Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge
C++
View on GitHub3,531

Compare all 30 related projects

PWhiddyPokemonRedExperiments