Reverse Dependencies of stable-baselines3

The following projects have a declared dependency on stable-baselines3:

• active-pre-train-ppg — Unsupervised pre-training with PPG
• ai4u — AI4U connect Godot and python applications compatible with gynasium
• amaze-benchmarker — Benchmark generator for sighted maze-navigating agents
• AssetAllocator — Train RL agents to manage a portfolio
• auto-graph-of-thoughts — Automated Graph of Thoughts
• basilsweepercrawler — no summary
• bauwerk — Simple building control environments for reinforcement learning.
• bluesky-gym — A gymnasium style environment for standardized Reinforcement Learning research in Air Traffic Management.
• bppy — BPpy: Behavioral Programming In Python
• cardio-rl — Cardio RL. In development...
• carl-bench — CARL- Contextually Adaptive Reinforcement Learning
• cfrl — no summary
• cleanrl — High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features
• commonpower — A package for the exploration of safe single/multi-agent reinforcement learning in smart grids.
• commonroad-geometric — Contains basic functionality for facilitating research on graph neural networks for autonomous driving and provides an interface between CommonRoad and Pytorch Geometric.
• conformer-rl — Deep Reinforcement Library for Conformer Generation
• coopihc — Two-agent component-based interaction environments for computational HCI with Python
• crgeo — Contains basic functionality for facilitating research on graph neural networks for autonomous driving and provides an interface between CommonRoad and Pytorch Geometric.
• cropgym — Reinforcement Learning Environment for Crop Management
• csle-agents — Reinforcement learning agents for CSLE
• csle-common — Common functionality of the Cyber Security Learning Environment (CSLE)
• diambra-arena — DIAMBRA™ Arena. Built with OpenAI Gym Python interface, easy to use, transforms popular video games into Reinforcement Learning environments
• double-cartpole-custom-gym-env — OpenAI Gym environment designed for training RL agents to balance double CartPole.
• dream-on-gym — no summary
• drone-2d-custom-gym-env — OpenAI Gym environment designed for training RL agents to control the flight of a two-dimensional drone.
• dsmc-tool — no summary
• eagerx-dcsc-setups — EAGERx interface to dcsc_setups.
• eagerx-examples — Code examples of EAGERx.
• eagerx-tutorials — Tutorials on how to use EAGERx.
• effective-horizon — Code for the NeurIPS 2023 paper "Bridging RL Theory and Practice with the Effective horizon" and the ICLR 2024 paper "The Effective Horizon Explains Deep RL Performance in Stochastic Environments".
• esmpi — Collection of Evolution Strategies optimizers with native MPI parallelization.
• eta-utility — A framework for researching energy optimization of factory operations
• eve-ml — Eve: make deep learning more interesting.
• experiment-lab — A suite of flexible experiments of a variety of different tasks.
• farmworld — Reinforcement Learning for Agriculture
• finrl-meta — FinRL­-Meta: A Universe of ­ Market En­vironments for Data­-Driven Financial Reinforcement Learning
• freqtrade — Freqtrade - Crypto Trading Bot
• godot-rl — A Deep Reinforcement Learning package for the Godot game engine
• graph-jsp-env — A flexible enviorment for job shop scheduling using the disjunctive graph apporach.
• gym-climate — Provide gym environments for reinforcement learning
• gym-conservation — Provide gym environments for reinforcement learning
• gym-fishing — Provide gym environments for reinforcement learning
• gym-flp — Implementation of facility layout problems in OpenAI Gym
• gym-idsgame — An Abstract Cyber Security Simulation and Markov Game for OpenAI Gym
• gymnasium-search-race — A reinforcement learning environment for the Search Race CG puzzle based on Gymnasium
• haxballgym-tools — no summary
• highrl — Two level RL for robots navigation
• huggingbutt — Client library to download and publish environments, agents on the huggingbutt.com hub
• hyperfetch — A tool to optimize and post hyperparameters for your reinforcement learning application. Currently available on Linux and macOS.
• HyperSweeper — Hydra sweeper integration of our favorite optimization packages, utilizing ask-and-tell interfaces.
• il-datasets — A package for creating IL datasets
• imitation — Implementation of modern reward and imitation learning algorithms.
• jsrl — Implementation of Jump-Start Reinforcement Learning with Stable Baselines3.
• kaggle-environments — Kaggle Environments
• loopquest — A Production Tool for Embodied AI.
• manipulation — MIT 6.421 - Robotic Manipulation
• mase-tools — Machine-Learning Accelerator System Exploration Tools
• mlpro-int-sb3 — MLPro: Integration StableBaselines3
• naturalminer — Mine data for patterns described in natural language
• nett-bd — A small example package
• nett-benchmarks — A testbed for comparing the learning abilities of newborn animals and autonomous artificial agents.
• nextgenjax — A JAX-based neural network library surpassing Google DeepMind's Haiku and Optax
• ntn-torch — ntn_torch is a library to build n-tuple neural network models using the framework of pytorch
• online-policy-adaptation-using-rollout — NOMS2024 paper: Online Policy Adaptation for Networked Systems Using Rollout
• openthechests — Training environment for reinforcement learning with event-based context
• opioidrl — Paper - Pytorch
• ostatslib — Open Statistical Analysis Agent Library
• paiagym — A platform to run Gymnasium or PettingZoo games with AI.
• pcgym — Reinforcement learning suite of process control problems.
• powderworld — A example Python package
• ptan — PyTorch reinforcement learning framework
• pyaiplayer — A tool to let human play game against AI model
• pybts — no summary
• pypowsybl_grid2opbackend — no summary
• pyrltools — A Python wrapper for RLtools
• qcd-gym — Quantum Circuit Designer: A gymnasium-based set of environments for benchmarking reinforcement learning for quantum circuit design.
• qgym — Reinforcement Learning Gym for Quantum Compilation
• qutip-qoc — The QuTiP quantum optimal control package
• qwertyenv — Gym and PettingZoo environments (Reinforcement Learning)
• qwop-gym — A Gymnasium environment for Benett Foddy's game QWOP
• RayEnvWrapper — OpenAi's gym environment wrapper to vectorize them with Ray
• releso — no summary
• rl-algo-impls — Implementations of reinforcement learning algorithms
• rlberry — An easy-to-use reinforcement learning library for research and education
• rltools — A Python wrapper for RLtools
• rltrade-test — Easy to use Reinforcement Library for finance
• roboquant — A fast algo-trading platform with support for machine learning based strategies
• sb3-contrib — Contrib package of Stable Baselines3, experimental code.
• sbx-rl — Jax version of Stable Baselines, implementations of reinforcement learning algorithms.
• scikit-decide — The AI framework for Reinforcement Learning, Automated Planning and Scheduling
• seals — Suite of Environments for Algorithms that Learn Specifications
• simulate — HuggingFace community-driven open-source library of simulation environments
• sinergym — The goal of sinergym is to create an environment following OpenAI Gym interface for wrapping simulation engines for building control using deep reinforcement learning.
• single-cartpole-custom-gym-env — OpenAI Gym environment designed for training RL agents to bring CartPole upright and its further balancing.
• siste-test — HyperFetch. A tool to optimize and fetch hyperparameters for your reinforcement learning application.
• starship-landing-gym — A Gym env for rocket landing.
• SuperSuit — Wrappers for Gymnasium and PettingZoo
• tensortrade-ng — TensorTrade-NG: A reinforcement learning library for training, evaluating, and deploying robust trading agents.
• tinyrl — A Python wrapper for RLtools
• tiptoestep — A reinforcement learning pakcage.