megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
☆148Feb 9, 2022Updated 4 years ago
Alternatives and similar repositories for megastep
Users that are interested in megastep are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Standard interface for entity based reinforcement learning environments.☆39Feb 28, 2024Updated 2 years ago
- Repo for the multi-agent PressurePlate environment☆19Feb 4, 2022Updated 4 years ago
- RL agent to play μRTS with Stable-Baselines3 and PyTorch☆27Jan 23, 2022Updated 4 years ago
- Accelerated replay buffers in JAX☆46Sep 17, 2022Updated 3 years ago
- A grid-world game engine for game AI research☆257Apr 9, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆332Dec 19, 2024Updated last year
- ☆21Dec 22, 2020Updated 5 years ago
- OpenAi's gym environment wrapper to vectorize them with Ray☆23May 25, 2023Updated 3 years ago
- C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.☆1,463Updated this week
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆190May 3, 2023Updated 3 years ago
- RL Environments in JAX 🌍☆901Apr 2, 2026Updated 2 months ago
- ☆10Jun 27, 2024Updated last year
- Codebase for BRDiv: Diverse teammate generation for ad hoc teamwork☆13May 2, 2024Updated 2 years ago
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments☆1,167Mar 27, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Collection of in-progress libraries for entity neural networks.☆29Jun 24, 2022Updated 3 years ago
- High throughput synchronous and asynchronous reinforcement learning☆1,001Jan 29, 2026Updated 4 months ago
- Code for the PAC-Bayes Control paper.☆13May 23, 2023Updated 3 years ago
- Learning Robust Dynamics Through Variational Sparse Gating☆20Oct 19, 2022Updated 3 years ago
- [ICLR 2024 oral] Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning☆30Mar 1, 2024Updated 2 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆180Jun 23, 2023Updated 2 years ago
- Train an agent to play VizDoom with multi sensory inputs. Trained using sample factory☆14Jul 9, 2021Updated 4 years ago
- Using a shared file to exchange data between Unity and Python☆13Oct 30, 2021Updated 4 years ago
- High-throughput simulation platform for Artificial Intelligence reseach☆229Dec 1, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆60Sep 22, 2022Updated 3 years ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆125Aug 22, 2024Updated last year
- Opinionated library for managing hyperparameters and mutable state of machine learning training systems.☆19Aug 4, 2023Updated 2 years ago
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,197May 18, 2026Updated last month
- Scaling scaling laws with board games.☆53Jul 17, 2023Updated 2 years ago
- ☆48Sep 13, 2021Updated 4 years ago
- DeepMind Alchemy task environment: a meta-reinforcement learning benchmark☆205Apr 5, 2023Updated 3 years ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆412Feb 10, 2026Updated 4 months ago
- A toolkit for practical Human-AI cooperation research☆14Apr 19, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Deep reinforcement learning implementation that trains AIs for the CodeCraft real-time strategy game.☆21May 22, 2023Updated 3 years ago
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆756Oct 26, 2022Updated 3 years ago
- A standalone release of DeepMind Lab's maze generator with Python bindings.☆69Oct 3, 2023Updated 2 years ago
- Gridworld for MARL experiments☆146Jan 29, 2021Updated 5 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆60Aug 4, 2022Updated 3 years ago
- RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random ne…☆465Apr 4, 2025Updated last year
- Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)☆503May 1, 2025Updated last year