Search Results for "python q learning"
Sort By:
Showing 31 open source projects for "python q learning"
View related business solutions-
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero
...This makes them hardly accessible for students, researchers and hackers. Many simple Python implementations can be found on Github, but none of them is able to beat a reasonable baseline on games such as Othello or Connect Four. As an illustration, the benchmark in the README of the most popular of them only features a random baseline, along with a greedy baseline that does not appear to be significantly stronger. -
2
ViZDoom
Doom-based AI research platform for reinforcement learning
ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular. ViZDoom is based on ZDOOM, the most popular modern source-port of DOOM. This means compatibility with a huge range of tools and resources that can be used to create custom scenarios, availability of detailed documentation of the engine and tools and support of Doom community.... -
3
DreamerV3
Mastering Diverse Domains through World Models
DreamerV3 is an open-source implementation of a reinforcement learning algorithm that uses world models to train intelligent agents capable of learning complex behaviors across many environments. The system works by building an internal model of the environment and then using that model to simulate possible future outcomes of actions, allowing the agent to learn from imagined experiences rather than only from real interactions. This approach enables the algorithm to efficiently learn... -
4
openage
Open source clone of the Age of Empires II engine
openage is a free cross-platform RTS game engine that provides the mechanics of Age of Empires. Using modern technologies as C++17, OpenGL/GLSL, Python, Qt5 and CMake allows people using GNU/Linux, BSD, macOS or Windows to play the game natively. Our aim is to make openage a platform for the original Age of Empires games providing the same look and feel, but with more features for modding and multiplayer. openage uses an open API powered by our human-readable configuration language nyan. We... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
Diplomacy Cicero
Code for Cicero, an AI agent that plays the game of Diplomacy
...It is designed to play the board game Diplomacy by combining open-domain natural language negotiation with strategic planning. The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant focused on no-press diplomacy) as described in the README. The codebase is implemented primarily in Python with performance-critical components in C++ (via pybind11 bindings) and is configured to run in a high‐GPU cluster environment. ... -
6
Koxinga
Like board game Jamaica
Minimum resolution is 1600x900. Koxinga is the game similar with board game Jamaica for human vs 5 computer player only. English game rule: https://sourceforge.net/projects/koxinga/files/Koxinga_English_User_Guide.pdf/download Chinese game rule: https://sourceforge.net/projects/koxinga/files/koxinga_chinese_manual.pdf/download 1) Q: Why won’t my piece move? A: You’re probably at a fork. On the map, look for two faint green arrows. Hover your mouse over them— they turn bright green. Click... -
7
AS Arrow
Add and Subtract game
AS refer to Add and Sub. During the game process, the card present as Arrow. Rule: Delete all card to win. User can drag and drop card from cards library to original 6 cards. At the game start, original 6 cards look like: d -b e- a -c f User can connect d, e, f cards. Once d and e are deleted, user can connect to b. Cards are positive for a, b, c, d, e, f. And then connecting card is negative. In the similar way, the next card is positive (add/plus), and then the card is... -
8
GemDash
Gem Dash aka Boulder or Dyna Blaster like 8-bit style game in Python
A Gem Dash is motivated from specific 8-bit games. Since it's my first code in Python, the old template gave me a good code basis to understand how to build game logic, use PyGame and create something that will work and I can finish. I can add even more game mechanics and changes. *_win include .exe (executable) *_mac include .app (in dmg, works independent) Requirements: - Python 3.13.2 or newer - Pygame 2.6.1 or newer ( terminal: pip install pygame ) Objective And Rules Of The Game: - Collect all the diamonds to open the exit to go to the next level... -
9
Bullet Physics SDK
Real-time collision detection and multi-physics simulation for VR
...In addition, the simulator can be entirely run on CUDA for fast rollouts, in combination with Augmented Random Search. This allows for 1 million simulation steps per second. It is highly recommended to use PyBullet Python bindings for improved support for robotics, reinforcement learning and VR. Use pip install pybullet and checkout the PyBullet Quickstart Guide. -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
Procgen
Procedurally-Generated Game-Like Gym-Environments
...The benchmark supports both “easy” and “hard” difficulty modes, letting researchers trade off computational cost vs challenge. The repo provides a C++ core for game logic and rendering (with support for gym/Gym3 wrappers) plus Python bindings and interactive mode for human play testing. -
11
Neural MMO
Code for the paper "Neural MMO: A Massively Multiagent Game..."
Neural MMO is a massively multi-agent simulation environment developed by OpenAI for reinforcement learning research. It provides a persistent, procedurally generated world where thousands of agents can interact, compete, and cooperate in real time. The environment is inspired by Massively Multiplayer Online Role-Playing Games (MMORPGs), featuring resource gathering, combat mechanics, exploration, and survival challenges. Agents learn behaviors in a shared ecosystem that supports long-term... -
12
Project Malmo
A platform for Artificial Intelligence experimentation on Minecraft
How can we develop artificial intelligence that learns to make sense of complex environments? That learns from others, including humans, how to interact with the world? That learns transferable skills throughout its existence, and applies them to solve new, challenging problems? Project Malmo sets out to address these core research challenges, addressing them by integrating (deep) reinforcement learning, cognitive science, and many ideas from artificial intelligence. The Malmo platform... -
13
ELF (Extensive Lightweight Framework)
An End-To-End, Lightweight and Flexible Platform for Game Research
ELF (Extensive, Lightweight, and Flexible) is a high-performance platform for reinforcement learning research that unifies simulation, data collection, and distributed training. A C++ core provides fast environments and concurrent actors, while Python bindings expose simple APIs for agents, replay, and optimization loops. It supports both single-agent and multi-agent settings, with batched stepping and shared-memory queues that keep GPUs saturated during training. -
14
2048 Python , AI , 1 or 2 players
py 2048, a well know 2048 clone board game
Written in Python 2.7.x and pygame1.9.1~2 compliant (at least) Python 3.4 HOW TO PLAY: keyboard UP, DOWN, LEFT, RIGHT, escape to quit increase your score shifting tiles with same number. the value of resulting tile is multiplied *2. CUSTOMISE YOUR GAME: edit py2048.cfg configuration file. you can: -Change Raws and Columns amount. -Change Random range value of new tile. -
15
ballspace
Ballspace is a Tux breakout game with a level editor.
Ballspace is a breakout game with a level editor. Ballspace is different of the classic games : ° You don't have no life in the game but you must protect all the Tuxs at the bottom of the screen. The game is finished as soon as you have no Tuxs to protect. ° You can pass to the next level as soon as you have destroy at least 75% of the bricks in using your super power... ° If a ball falls, you don't lose a life but at worst one or all the Tuxs... The keys of the game : left and... -
16
Golden Point
A simple, console-based card game, similar to some other card games.
Golden Point is a simple card game, similar to some other popular card games. The main goal of the game is to get more points then your opponent, but in the same time not to get more than 21 ("Golden Point"). During the game you get cards, which have next values: 6, 7, 8, 9, 10 - according to numbers in it's names; J - 2 points; Q - 3 points; K - 4 points; A - 11 points. In the beginning of the game you get 2 cards, and if your total points are less than 21, you can take more... -
17
pynvaders
Invaders like game, written in Python with Curses... :)
Invaders like game, written in Python with Curses... :) Also, this was a learning project for me to Python language. -
18
The goal of this project is to create a Python implementation of standard Riichi Mahjong. Code shall be properly documented and serve as a learning tool for other developers.
-
19
Strum aims to improve your musical skills on stringed instruments; learning scales, chord construction, and how to find them on various instruments with many tunings.
-
20
Very compact Tetris game for those who want to play where/when they should not: only a tiny gaming area (even 40px high) your headmaster will hardly notice (in case, just press Q or Escape).
-
21
"Roberge's Used Robot (RUR) : a Python Learning Environment" is a Python implementation of a "robot environment" as introduced by R. Pattis in 1981. **It is obsolete.** See https://github.com/aroberge/rur-ple
-
22
...This game is played like the game known as Concentration, Memory or Match. There are multiple levels, a highscore, and soundtrack. This game might be helpful to someone learning Python and pyGame
-
23
General purpose agents using reinforcement learning. Combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. Intended to be an out-of-the-box solution for roboticists and game developers.
-
24
Capivar Hunter is a simple 3d shooter written in Python/OpenGL intended as a learning platform to Game Development, Python and 3d Programming. Although it should be at least somewhat funny, the main objective of it is being simple and easy to extend.
-
25
This is a PacMan Clone that we intend to program for learning Game Development. Feel free to give us your advice and tell us if you like playing it. Este es un clon del Pacman que queremos programar para aprender a Desarrollar Juegos.
