alex-petrenko / megaverse
High-throughput simulation platform for Artificial Intelligence reseach
☆222Updated 2 years ago
Alternatives and similar repositories for megaverse:
Users that are interested in megaverse are comparing it to the libraries listed below
- megastep helps you build 1-million FPS reinforcement learning environments on a single GPU☆133Updated 3 years ago
- A customisable 2D platform for agent-based AI research☆426Updated last year
- ☆256Updated 2 years ago
- Benchmarking the Spectrum of Agent Capabilities☆423Updated last year
- impact-driven-exploration☆129Updated last year
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆185Updated last year
- [ICML 2020] PyTorch Code for "One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control"☆226Updated 2 years ago
- DrQ-v2: Improved Data-Augmented Reinforcement Learning☆379Updated 2 years ago
- Repository for the paper "Planning to Explore via Self-Supervised World Models"☆218Updated 2 years ago
- Libraries, tools and tasks created and used at DeepMind Robotics.☆361Updated 3 months ago
- Robotics Gym Environments☆412Updated last year
- A set of 13 diverse machine-learning tasks that require memory to solve.☆221Updated 3 years ago
- A networking protocol for agent-environment communication☆99Updated last month
- Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"☆170Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆297Updated last year
- ☆121Updated 7 months ago
- Convert DeepMind Control Suite to OpenAI gym environments.☆83Updated 5 years ago
- PyTorch implementation of DreamerV2 model-based RL algorithm☆216Updated last year
- ☆32Updated 3 years ago
- Implementation of advantage-weighted regression.☆184Updated 4 years ago
- DeepMind Alchemy task environment: a meta-reinforcement learning benchmark☆200Updated last year
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆130Updated 7 months ago
- Dream to Control: Learning Behaviors by Latent Imagination☆526Updated 3 years ago
- OpenAI Gym wrapper for the DeepMind Control Suite☆211Updated 10 months ago
- ☆100Updated last year
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆246Updated 2 years ago
- A grid-world game engine for game AI research☆239Updated 11 months ago
- PAIRED in PyTorch 🔥☆58Updated 2 years ago
- Code for the paper "Phasic Policy Gradient"☆259Updated last year
- The submission template for the MineRL Competition @ NeurIPS 2021. Clone this to make a new submission!☆92Updated 3 years ago