Reverse Dependencies of gymnasium
The following projects have a declared dependency on gymnasium:
- graph-jsp-env — A flexible enviorment for job shop scheduling using the disjunctive graph apporach.
- GreenLightPlus — Greenhouse Simulation and Optimization Toolkit
- gym-aloha — A gym environment for ALOHA
- gym-anytrading — no summary
- gym-csle-apt-game — OpenAI gym reinforcement learning environment of a Dynkin (Optimal stopping) APT game in CSLE
- gym-csle-cyborg — OpenAI gym reinforcement learning environment wrapper for CybORG
- gym-csle-intrusion-response-game — OpenAI gym reinforcement learning environment of an intrusion response game in CSLE
- gym-csle-stopping-game — OpenAI gym reinforcement learning environment of a Dynkin (Optimal stopping) game in CSLE
- gym-distractions — Environment with different disk dynamics for distractions in RL environments
- gym-electric-motor — A Farama Gymnasium environment for electric motor control.
- gym-jiminy — Python-native OpenAI Gym interface between Jiminy open-source simulator and Reinforcement Learning frameworks.
- gym-mtsim — no summary
- gym-PBN — A Gymnasium environment modelling Probabilistic Boolean Networks and Probabilistic Boolean Control Networks.
- gym-pusht — A gymnasium environment for PushT.
- gym-saturation — Gymnasium environments for saturation provers
- gym-simplegrid — Simple Gridworld Environment for Gymnasium
- gym-trading-env — A simple, easy, customizable Open IA Gym environments for trading.
- gym-xarm — A gym environment for xArm
- gymize — Unity and Python Reinforcement and Imitation Learning with Gymnasium and PettingZoo API.
- gymnasium-2048 — A reinforcement learning environment for the 2048 game based on Gymnasium
- gymnasium-connect-four — A connect 4 (connect four) environment for OpenAI Gym and Gymnasium
- gymnasium-minigrid — A mini grid environment for OpenAI Gym and Gymnasium
- gymnasium-quadruped — Gymnasium environment for training quadruped legged robots
- gymnasium-snake-game — Snake game for Farama Gymnasium
- gymnax — JAX-compatible version of Open AI's gym environments
- gymprecice — A framework to designe Reinforcement Learning (RL) environments for Active Flow Control (AFC), as well as a playground to train Deep Reinforcement Learning (DRL) algorithms for AFC applications.
- gymxq — no summary
- haruna — no summary
- hedging-gym — HedgingGym is a reinforcement learning environment for training and testing hedging strategies.
- Helx — Interoperate among reinforcement learning libraries with jax, pytorch, gym and dm_env
- HELX-envs — Interoperate among reinforcement learning libraries with jax, pytorch, gym and dm_env
- highway-env — An environment for simulated highway driving tasks.
- humemai — A Machine With Human-Like Memory Systems.
- imitation — Implementation of modern reward and imitation learning algorithms.
- inf581 — Tool functions for INF581.
- instruct-goose — Implementation of Reinforcement Learning from Human Feedback (RLHF)
- intercode-bench — The official InterCode benchmark package - a framework for interactive code tasks
- jit-env — A Jax interface for Reinforcement Learning environments.
- joyrl — A Library for Deep Reinforcement Learning
- jsbgym — A package of reinforcement learning environments for flight control using the JSBSim flight dynamics model.
- jsspetri — JSSPetri: Job Shop Scheduling with Petri Nets and Reinforcement learning multi ojective support
- kaggle-environments — Kaggle Environments
- lanro-gym — Gymnasium multi-goal environments for goal-conditioned and language-conditioned deep reinforcement learning build with PyBullet
- letterenv — no summary
- libwebarena — This is an unofficial, use-at-your-own risks port of the webarena benchmark, for use as a standalone library package.
- LightZero — A lightweight and efficient MCTS/AlphaZero/MuZero algorithm toolkits.
- llamagym — Fine-tune LLM agents with online reinforcement learning
- logistics-or-gym — or-problems formulated as gym environments to solve logisitcal-problems
- loopquest — A Production Tool for Embodied AI.
- luxai-s2 — The Lux AI Challenge Season 2
- mal-simulator — A MAL compliant simulator.
- marl-aquarium — Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms
- Marl-Factory-Grid — A framework to research MARL agents in various setings.
- Marl-Neon-Grid — A collection of MARL gridworlds to study coordination and cooperation.
- marlben — Marlben is a multi-agent reinforcement learning benchmark based on the NeuralMMO game engine.
- matex — A collection of reinforcement learning algorithms
- mathy — Mathy - RL environments for solving math problems step-by-step
- mathy-envs — Learning environments for solving math problems step-by-step
- matrix-mdp-gym — An OpenAI gym / Gymnasium environment to seamlessly create discrete MDPs from matrices.
- maze-world — Random maze environments with different size and complexity for reinforcement learning and planning research. This is in-particular to investigate generalization and planning ability in dynamically changing environment.
- mbrl — A PyTorch library for model-based reinforcement learning research
- mcts-simple — Python package that helps to quickly implement MCTS to solve reinforcement learning problems.
- memory-gym — A gym that contains the memory benchmarks Mortar Mayhem, Mystery Maze and Searing Spotlights
- metadrive-simulator — An open-ended driving simulator with infinite scenes
- mevo — Evolutionary Algorithms in Python
- microvault — Microvault - RL for Navigation
- Minari — A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities.
- minigrid — Minimalistic gridworld reinforcement learning environments.
- miniwob — A web interaction benchmark for reinforcement learning.
- mlopsrobotics — no summary
- mlpro-int-gymnasium — MLPro: Integration Gymnasium
- mo-gymnasium — A standard API for MORL and a diverse set of reference environments.
- mobile-env — mobile-env: An Open Environment for Autonomous Coordination in Wireless Mobile Networks
- ModularDQN — An implementation of the DQN algorithm and all improvments of rainbow DQN
- momaland — A standard API for Multi-Objective Multi-Agent Decision making and a diverse set of reference environments.
- moojoco — A unified framework for implementing and interfacing with MuJoCo and MuJoCo-XLA simulation environments.
- morl-baselines — Implementations of multi-objective reinforcement learning (MORL) algorithms.
- mpcrl — Reinforcement Learning with Model Predictive Control
- MPSPEnv — A reinforcement learning environment for the Multi Port Stowage Planning problem
- mu-alpha-zero-library — Library for running and training MuZero and AlphaZero models.
- muax — A library written in Jax that provides help for using DeepMind's mctx on gym-style environments.
- multigrid — Fast multi-agent gridworld reinforcement learning environments.
- nasim — A simple and fast simulator for remote network pen-testing
- neorl2 — no summary
- NeuralPlayground — The standardised environment for the hippocampus and entorhinal cortex models
- noisyenv — Simple noisy environment augmentation for reinforcement learning
- online-policy-adaptation-using-rollout — NOMS2024 paper: Online Policy Adaptation for Networked Systems Using Rollout
- openrl — unified reinforcement learning framework
- padlock-env — Awesome padlock_env created by cyprienc
- palaestrai — A Training Ground for Autonomous Agents
- palaestrai-environments — A set of example environments for palaestrAI.
- panda-gym — Set of robotic environments based on PyBullet physics engine and gymnasium.
- parking-env — An environment for simulated parking lot tasks.
- pcgym — Reinforcement learning suite of process control problems.
- PettingZoo — Gymnasium for multi-agent reinforcement learning.
- pgeon-xai — pgeon (or pgeon-xai) is a Python package that produces explanations for opaque agents using Policy Graphs (PGs)
- pgtg — Python simulation of a driving challange. Compatible with the Gymnasium API standard.
- playgroundrl-envs — The environments hosted on Playground RL
- plstab — no summary
- pogema — Partially Observable Grid Environment for Multiple Agents