Theo-Jaunet/MemoryReduction
Online exploration of memory reduction strategies of a DRL agent trained to solve a navigation task on ViZDoom
This project lets you interactively explore how different memory reduction techniques impact the performance of an AI agent trained to navigate complex 3D environments, specifically a game like Doom. You can input various memory strategies and observe in real-time how the agent's behavior changes. This tool is for AI researchers and game AI developers interested in optimizing reinforcement learning models for resource-constrained environments.
No commits in the last 6 months.
Use this if you are researching or developing AI agents and want to understand the trade-offs of different memory reduction strategies on their navigation performance.
Not ideal if you are looking for a general-purpose AI development library or a tool for training new reinforcement learning models from scratch.
Stars
7
Forks
—
Language
JavaScript
License
—
Category
Last pushed
Jan 06, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Theo-Jaunet/MemoryReduction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Talendar/flappy-bird-gym
An OpenAI Gym environment for the Flappy Bird game
Farama-Foundation/ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
chris-chris/pysc2-examples
StarCraft II - pysc2 Deep Reinforcement Learning Examples
aleju/mario-ai
Playing Mario with Deep Reinforcement Learning
gsurma/atari
AI research environment for the Atari 2600 games 🤖.