andyljones / megastep
megastep helps you build 1-million FPS reinforcement learning environments on a single GPU
β133Updated 3 years ago
Alternatives and similar repositories for megastep:
Users that are interested in megastep are comparing it to the libraries listed below
- impact-driven-explorationβ130Updated last year
- PAIRED in PyTorch π₯β58Updated last year
- β119Updated last year
- JAX implementations of core Deep RL algorithmsβ79Updated 2 years ago
- Baselines for gymnax π€β65Updated last year
- β295Updated 2 months ago
- Modular framework for Reinforcement Learning in pythonβ171Updated 2 years ago
- A library that makes Evolutionary Strategies (ES) simple to use.β181Updated 3 years ago
- A grid-world game engine for game AI researchβ239Updated 10 months ago
- Benchmarking TD3 and DDPG on PyBulletβ52Updated 5 years ago
- Code for the paper, "Learning Human Objectives by Evaluating Hypothetical Behavior"β83Updated 5 years ago
- A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer (https://arxiβ¦β71Updated 4 years ago
- Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"β170Updated last year
- β85Updated 4 years ago
- A collection of RL algorithms written in JAX.β95Updated 2 years ago
- Vectorization techniques for fast population-based training.β55Updated 2 years ago
- Datasets for data-driven deep reinforcement learning with PyBullet environmentsβ148Updated 3 years ago
- Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPOβ195Updated 2 years ago
- Convert DeepMind Control Suite to OpenAI gym environments.β83Updated 5 years ago
- My solution to the Unity Obstacle Tower Challengeβ136Updated 3 years ago
- A curated list of reinforcement learning environments and frameworks.β50Updated 6 years ago
- OpenAI Gym wrapper for ViZDoom enviromentsβ69Updated 3 years ago
- Accelerated Quality-Diversityβ275Updated this week
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β53Updated 2 years ago
- Revisiting Rainbowβ74Updated 3 years ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ138Updated 3 months ago
- β100Updated last year
- Neuro-evolution for OpenAI Gym environmentsβ56Updated 4 years ago
- Website for Quality-Diversity optimisation algorithmsβ43Updated 5 months ago
- DeepMind Alchemy task environment: a meta-reinforcement learning benchmarkβ199Updated last year