andyljones / megastepLinks
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
☆137Updated 3 years ago
Alternatives and similar repositories for megastep
Users that are interested in megastep are comparing it to the libraries listed below
Sorting:
- impact-driven-exploration☆131Updated last year
- A grid-world game engine for game AI research☆244Updated last year
- ☆305Updated 6 months ago
- Baselines for gymnax 🤖☆67Updated 2 years ago
- JAX implementations of core Deep RL algorithms☆82Updated 3 years ago
- Modular framework for Reinforcement Learning in python☆173Updated 2 years ago
- PAIRED in PyTorch 🔥☆62Updated 2 years ago
- Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"☆172Updated 2 years ago
- ☆123Updated last year
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆57Updated 2 years ago
- ☆101Updated last year
- A collection of RL algorithms written in JAX.☆100Updated 3 years ago
- Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO☆201Updated 2 years ago
- Convert DeepMind Control Suite to OpenAI gym environments.☆87Updated 5 years ago
- Repository for the paper "Planning to Explore via Self-Supervised World Models"☆221Updated 2 years ago
- Real-World RL Benchmark Suite☆356Updated 4 years ago
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆251Updated 3 years ago
- Vectorized interface for reinforcement learning environments☆140Updated 2 years ago
- Library to compare and evaluate reward functions☆67Updated last year
- A bare-bones Python library for quality diversity optimization.☆231Updated this week
- OpenAI Gym wrapper for ViZDoom enviroments☆69Updated 4 years ago
- Benchmarking TD3 and DDPG on PyBullet☆53Updated 6 years ago
- DeepMind Alchemy task environment: a meta-reinforcement learning benchmark☆199Updated 2 years ago
- A library that makes Evolutionary Strategies (ES) simple to use.☆180Updated 4 years ago
- Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.☆131Updated 10 months ago
- Accelerated Quality-Diversity☆307Updated last month
- A networking protocol for agent-environment communication☆100Updated 5 months ago
- ☆84Updated 4 years ago
- Benchmarking the Spectrum of Agent Capabilities☆454Updated last year
- From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..☆242Updated last year