CPU-oriented Python library for discrete Active Inference experiments in radCAD and cadCAD: deterministic grid worlds, multi-agent transitions, generative-model helpers, and fail-closed validation.

python simulation reproducible-research inference generative-model grid-world active agent-based-modeling active-inference cadcad radcad expected-free-energy

Updated Aug 9, 2026
Python

LijunSun90 / MatrixWorld

Star

MatrixWorld: A pursuit-evasion platform for safe multi-agent coordination and autocurricula

grid-world large-scale safety-critical adversarial-learning pursuit-evasion multi-agent-path-finding co-evolution collision-resolution arms-race multi-agent-environment autocurricula safe-multiagent-reinforcement-learning

Updated Feb 26, 2025
Python

nkrgit / Fleet-Scheduling-using-MADDPG-Multi-Agent-RL

Star

Developed a Multi-Agent DDPG to solve Vehicle Scheduling problem.

q-learning grid-world fleet-management keras-tensorflow openai-gym-environments maddpg

Updated Feb 12, 2023
Jupyter Notebook

quanghuyle3 / Runners_Agent_Based_Model

Star

Agent-based activity generation of runners for city infrastructure planning.

visualization simulation grid-world agent-based-modeling runners city-planning osmnx mesa3d

Updated Aug 28, 2021
Python

u-t-autonomous / gridsim

Star

A grid world simulation environment

grid simulation pygame mdp grid-world gridworld

Updated Nov 20, 2017
Python

hmeretti / grid-world

Star

exploring reinforcement learning techniques from scratch, in a simple environment

reinforcement-learning grid-world dynamic-programming

Updated Jan 30, 2023
Jupyter Notebook

See a program learn the best actions in a grid-world to get to the target cell, and even run through the grid in real-time! This is a Q-Learning implementation for 2-D grid world using both epsilon-greedy and Boltzmann exploration policies.

python machine-learning reinforcement-learning grid-world epsilon-greedy boltzmann-exploration

Updated Feb 4, 2023
Python

jedarden / ai-code-battle

Star

AI bot programming challenge platform — write bots that compete in a shared grid world

go game-engine multiplayer competitive-programming grid-world programming-game http-api bot-programming

Updated Aug 28, 2026
Go

LijunSun90 / pursuitMatrixWorld

Star

Multi-agent pursuit in matrix world (pursuitMW)

benchmark environment reinforcement-learning decision-making coordination uncertainty multi-agent swarm grid-world pursuit self-organization predator-prey swarm-intelligence pursuit-evasion multi-agent-reinforcement-learning partially-observable-environment swarm-behaviour

Updated Dec 23, 2022
Python

ashkanfeyzollahi / bellman-grid-solver

Star

🤖 Solve deterministic grid worlds/mazes using bellman equation

maze grid-world maze-solver bellman-equation

Updated Sep 14, 2025
Python

sintefneodroid / Examples

Star

Example Implementations of Reinforcement Learning Environments using Neodroid

agent learning fun world grid reinforcement-learning ml grid-world rl gridworld hacktoberfest gridworld-environment

Updated Dec 8, 2022
C#

IBM / IBM-Extended-Markov-Ratio-Decision-Process

Star

This repo includes code referenced in the paper A Rigorous Risk-aware Linear Approach to Extended Markov Ratio Decision Processes with Embedded Learning by Alexander Zadorojniy, Takayuki Osogami, and Orit Davidovich to appear in IJCAI 2023.

grid-world ray markov-decision-processes optimization-algorithms ibm-research-ai