openai / procgen
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
☆1,036Updated last year
Alternatives and similar repositories for procgen:
Users that are interested in procgen are comparing it to the libraries listed below
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆559Updated 2 years ago
- Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research☆519Updated 4 months ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆718Updated this week
- Tools for accelerating safe exploration research.☆511Updated last year
- A Python interface for reinforcement learning environments☆354Updated 2 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆622Updated 4 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆523Updated 3 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,159Updated this week
- A customisable 2D platform for agent-based AI research☆423Updated last year
- Mastering Atari with Discrete World Models☆915Updated last year
- A simple OpenAI Gym environment for single and multi-agent reinforcement learning☆735Updated last year
- Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.☆837Updated 3 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆396Updated last year
- A suite of test scenarios for multi-agent reinforcement learning.☆643Updated last week
- High throughput synchronous and asynchronous reinforcement learning☆854Updated 2 weeks ago
- Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research☆712Updated this week
- DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (…☆463Updated 9 months ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆662Updated 8 months ago
- Benchmarking the Spectrum of Agent Capabilities☆401Updated 11 months ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,514Updated 9 months ago
- Code for the paper "Exploration by Random Network Distillation"☆888Updated 4 years ago
- Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games☆540Updated last year
- Code for the paper "Large-Scale Study of Curiosity-Driven Learning"☆804Updated 3 years ago
- A PyTorch Platform for Distributed RL☆744Updated 3 years ago
- Automatic object XML generation for Mujoco☆534Updated 5 months ago
- A PyTorch library for building deep reinforcement learning agents.☆648Updated 10 months ago
- MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.☆2,908Updated last year
- SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's arch…☆799Updated 2 years ago
- World Models Experiments☆633Updated 2 years ago
- A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface☆375Updated last year