Reverse Dependencies of gym
The following projects have a declared dependency on gym:
- lerobot — Le robot is learning
- Lightning — The Deep Learning framework to train, deploy, and ship AI products Lightning fast.
- lightning-bolts — Lightning Bolts is a community contribution for ML researchers.
- lightRaven — Library for Fast Offline RL Analysis with Minimum Dependencies
- lips-benchmark — LIPS : Learning Industrial Physical Simulation benchmark suite
- llcp-env — A OpenAI Gym Env for gym
- lrl — lrl: Learn Reinforcement Learning
- lsm-params-env — A openAI Gym Env for lsm
- lt-env — A OpenAI Gym Env for gym
- ltron — LEGO interactive machine learning environment.
- ludus — Reinforcement learning library to expediate application and research
- luwi-gym-foo — A OpenAI Gym Env for foo
- luxai2022 — The Lux AI Challenge Season 2
- lxy-env — A OpenAI Gym Env for lxy
- lyn-env — A OpenAI Env for lyn
- lzy-stock-env — 机器学习作业用的股票数据环境
- MA-bidding — Multi-Agent Goal-Driven Bidding Environment
- ma-gym — A collection of multi agent environments based on OpenAI gym.
- macad-gym — Learning environments for Multi-Agent Connected Autonomous Driving (MACAD) with OpenAI Gym compatible interfaces
- machin — Reinforcement learning library
- machina-rl — machina is a library for a deep reinforcement learning.
- magical-il — MAGICAL is a benchmark suite for robust imitation learning
- malmoenv — A gym environemnt for Malmo
- mancala — Mancala written in Python, playable in CLI (GUI coming soon)!
- manimalai — AnimalAI clone learning environment
- many-world — Many-world Environment, for Object-centric RL
- Mario-GYM — Preprocessed Retro GYM for Super Mario Bros.
- marlenv — no summary
- marlware — Multi-Robot Warehouse environment for reinforcement learning
- mars-gym — Framework Code for the RecSys 2020 entitled 'MARS-Gym: A Gym framework to model, train, and evaluate recommendationsystems for marketplaces'.
- MASB — Multi-Agent Goal-Driven Bidding Environment
- mathy-envs — Learning environments for solving math problems step-by-step
- maze-rl — MazeRL is a development framework for building applied reinforcement learning systems, addressing real-world decision problems. It supports the complete development life cycle of RL applications, ranging from simulation engineering up to agent development, training and deployment.
- mazeexplorer — Customisable 3D benchmark for assessing generalisation in Reinforcement Learning.
- mazenv — Maze environments for Reinforcement Learning
- mdp-playground — A python package to design and debug RL agents
- meta-monsterkong — meta_monsterkong: samples a new map uniformly at random from a directory of generated maps
- metadrive-simulator — An open-ended driving simulator with infinite scenes
- metagym — MetaGym: environments for benchmarking Reinforcement Learning and Meta Reinforcement Learning
- mibexx-gym-minesweeper — Gym Environment for Minesweeper
- mindspore-rl — A MindSpore reinforcement learning framework.
- minedojo — research project
- minerl-wrappers — minerl-wrappers compiles common wrappers and standardizes code for reproducibility in the MineRL environment!
- minigym — more gym environments
- minihack — MiniHack The Planet: A Sandbox for Open-Ended Reinforcement Learning Research
- minihex — The game of Hex implemented for reinforcement learning in the OpenAI gym framework. Optimized for rollout speed.
- miniworld — no summary
- mlagents-envs — Unity Machine Learning Agents Interface
- mlopsrobotics — no summary
- mo-gym — Environments for Multi-Objective RL.
- mobile-env-rl — A Universal Platform for Training and Evaluation of Mobile Interaction
- mobileprint — GUI for measuring human performance on mobile construction task
- mobileprint-test — GUI for measuring human performance on mobile construction task
- modular-rl — ModularRL is a Python library for creating and training reinforcement learning agents using various algorithms. The library is designed to be easily customizable and modular, allowing users to quickly set up and train agents for various environments without being limited to a specific algorithm.
- moki-panda — An OpenAI Gym Env for Panda
- MorEpiSim — a Reinforcement Learning based Epidemic control simulation environment
- mozi-ai — 墨子AI:军事人工智能领航者, developed by HSFW
- mtenv — MTEnv: MultiTask Environments for Reinforcement Learning
- mu-alpha-zero-library — Library for running and training MuZero and AlphaZero models.
- mujoco-maze — Simple maze environments using mujoco-py
- multirotor — Simulation testbed for multirotor vehicles.
- MultiTaxiLib — My short description for my project.
- muscledagents — Muscle rigged models and environments for machine learning experiments.
- mushroom-rl — A Python toolkit for Reinforcement Learning experiments.
- muzero-baseline — Baseline implementation of MuZero agent
- mvc — Cleanest Deep Reinforcement Learning Implementation Based on Web MVC
- nav-env — nav_env
- nav2d — 2D Navigation Gym Environment
- navigation-2d — 2d navigation environment with Box2D
- navsim — Navigation Simulator
- navsim-envs — Navigation Simulator Environments
- navstack-gym — Simulation environment of task with autonomous mobile robot using Navigation Stack
- nclustenv — Gym environments to learn biclustering and triclustering tasks using reinforcement learning.
- Neodroid — Python interface for the Neodroid platform, an API for communicating with a Unity Game process for a feedback response loop
- NeodroidAgent — Reinforcement learning agent implementations, intended for use with the Neodroid platform
- neorl — NeuroEvolution Optimisation with Reinforcement Learning
- neroRL — A library for Deep Reinforcement Learning (PPO) in PyTorch
- nes-py — An NES Emulator and OpenAI Gym interface
- nethack-neural — no summary
- neural-mmo — Neural MMO is a massively multiagent environment for artificial intelligence research inspired by Massively Multiplayer Online (MMO) role-playing games
- nevergrad — A Python toolbox for performing gradient-free optimization
- nevolution-risk — Python Gym Environment for the popular Risk game
- nevopy — An open source neuroevolution framework for Python.
- nextdataAI — no summary
- nlp-gym — NLPGym - A toolkit for evaluating RL agents on Natural Language Processing Tasks
- nmmo — Neural MMO is a platform for multiagent intelligence research inspired by Massively Multiplayer Online (MMO) role-playing games. Documentation hosted at neuralmmo.github.io.
- nnabla-rl — Deep reinforcement learning library built on top of Neural Network Libraries
- nnrl — Top-level package for NN RL.
- nsmr — Navigation Simulator for Mobile Robot
- numpy-ml — Machine learning in NumPy
- obstacle — Obstacle Tower Challenge Environment
- obstacle-tower-env — no summary
- offlinerl — A Library for Offline RL(Batch RL)
- online-policy-adaptation-using-rollout — NOMS2024 paper: Online Policy Adaptation for Networked Systems Using Rollout
- openmodelica-microgrid-gym — OpenModelica Microgrid Gym
- openrl — unified reinforcement learning framework
- or-gym — OR-Gym: A set of environments for developing reinforcement learning agents for OR problems.
- ori-optimize — a environment that controls STL model rotate to reach the maximal 3D printing quality.
- ori-optimize-linux — a environment that controls STL model rotate to reach the maximal 3D printing quality.
- OriOptimization — no summary