alex-petrenko / megaverse
High-throughput simulation platform for Artificial Intelligence reseach
☆219Updated last year
Related projects ⓘ
Alternatives and complementary repositories for megaverse
- megastep helps you build 1-million FPS reinforcement learning environments on a single GPU☆133Updated 2 years ago
- Benchmarking the Spectrum of Agent Capabilities☆390Updated 10 months ago
- impact-driven-exploration☆128Updated last year
- A customisable 2D platform for agent-based AI research☆422Updated last year
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆181Updated last year
- ☆245Updated 2 years ago
- Repository for the paper "Planning to Explore via Self-Supervised World Models"☆215Updated last year
- [ICML 2020] PyTorch Code for "One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control"☆221Updated last year
- Starter Kit for NeurIPS 2020 - Procgen Competition on AIcrowd☆90Updated last year
- Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"☆169Updated last year
- A tool for recording RL trajectories.☆94Updated last week
- ☆116Updated last year
- Libraries, tools and tasks created and used at DeepMind Robotics.☆345Updated 2 months ago
- A networking protocol for agent-environment communication☆90Updated last month
- Convert DeepMind Control Suite to OpenAI gym environments.☆83Updated 4 years ago
- ☆118Updated 3 months ago
- DrQ-v2: Improved Data-Augmented Reinforcement Learning☆355Updated 2 years ago
- 🎢 Creating and sharing simulation environments for embodied and synthetic data research☆190Updated last year
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆481Updated 3 months ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆126Updated 3 months ago
- Evaluating long-term memory of reinforcement learning algorithms☆133Updated last year
- PyTorch implementation of DreamerV2 model-based RL algorithm☆209Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆286Updated 10 months ago
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆79Updated last year
- IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks☆503Updated last year
- A set of 13 diverse machine-learning tasks that require memory to solve.☆221Updated 3 years ago
- OpenAI Gym wrapper for the DeepMind Control Suite☆205Updated 6 months ago
- OffWorld Gym: Open-Access Physical Robotics Environment for Real-World Reinforcement Learning Benchmark and Research☆56Updated last year
- Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".☆80Updated 8 months ago
- Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined wit…☆186Updated 3 years ago