ma-gym
crafter
| ma-gym | crafter | |
|---|---|---|
| 2 | 2 | |
| 522 | 348 | |
| - | - | |
| 6.1 | 5.4 | |
| 3 months ago | 4 months ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ma-gym
-
Tensorflow and OpenAI Gym for Multi-Agent Reinforcement Learning?
Of course I conducted research (or rather... searched on google :)) before making this post. I found a simple third party gym environment that implements multi-agent rl called 'ma-gym' (https://github.com/koulanurag/ma-gym) but I'm not quite sure how I would train two Agents and let them play inside one environment.
-
How do you train Agent for something like Chess or Game of the Generals?
There are projects working on a multi agent version of gym. Maybe you find some inspiration there.
crafter
-
[R] Benchmarking the Spectrum of Agent Capabilities: They introduce Crafter, an open world survival game with visual inputs that evaluates a wide range of general abilities within a single environment.
Repo for Crafter: https://github.com/danijar/crafter
- Crafter - Open world survival environment for reinforcement learning.
What are some alternatives?
mcts-general - General Python implementation of Monte Carlo Tree Search for the use with Open AI Gym environments.
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Minigrid - Simple and easily configurable grid world environments for reinforcement learning
FoliClientInstaller - Installs the Foli Client Minecraft modpack
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
ITAQA-air-quality-aggregator - Framework to collect, aggregate and process air pollution data from different sources (Italy regions)
GoBigger - [ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.
portfolio-management - Repository for portfolio management using Pytorch, SQLAlchemy and XArray. The management is done using the reinforcement learning algorithm "Soft Actor-Critic".
rlcard - Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
dreamerv2 - Mastering Atari with Discrete World Models
ecobalyse - Accélerer la mise en place de l'affichage environnemental
dreamerv3 - Mastering Diverse Domains through World Models