openai / procgen
Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
☆1,023Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for procgen
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆703Updated 3 weeks ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆394Updated last year
- Neural MMO - A Massively Multiagent Environment for Artificial Intelligence Research☆522Updated 2 months ago
- Tools for accelerating safe exploration research.☆506Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination☆609Updated 4 years ago
- Benchmarking the Spectrum of Agent Capabilities☆388Updated 9 months ago
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆558Updated last year
- Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research☆708Updated 2 weeks ago
- A Python interface for reinforcement learning environments☆346Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination☆513Updated 3 years ago
- High throughput synchronous and asynchronous reinforcement learning☆830Updated this week
- Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.☆830Updated 3 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,125Updated this week
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆654Updated 6 months ago
- A customisable 2D platform for agent-based AI research☆422Updated last year
- DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (…☆456Updated 7 months ago
- A suite of test scenarios for multi-agent reinforcement learning.☆621Updated 2 weeks ago
- Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.☆870Updated 11 months ago
- Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official imp…☆1,222Updated 11 months ago
- SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's arch…☆799Updated last year
- MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.☆2,875Updated 11 months ago
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.☆3,818Updated this week
- World Models Experiments☆624Updated 2 years ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆480Updated 3 months ago
- A simple OpenAI Gym environment for single and multi-agent reinforcement learning☆727Updated 11 months ago
- Automatic object XML generation for Mujoco☆522Updated 3 months ago
- Mastering Atari with Discrete World Models☆899Updated last year
- A PyTorch Platform for Distributed RL☆738Updated 3 years ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,512Updated 7 months ago
- Real-World RL Benchmark Suite☆347Updated 4 years ago