google-deepmind / ai-safety-gridworldsLinks
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
☆611Updated 3 years ago
Alternatives and similar repositories for ai-safety-gridworlds
Users that are interested in ai-safety-gridworlds are comparing it to the libraries listed below
Sorting:
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning ag…☆663Updated 5 years ago
- Code for the paper "Emergent Complexity via Multi-agent Competition"☆816Updated 2 years ago
- Code for the paper "Meta-Learning Shared Hierarchies"☆616Updated last year
- hanabi_learning_environment is a research platform for Hanabi experiments.☆651Updated 2 years ago
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆1,005Updated 6 years ago
- A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface☆381Updated 2 years ago
- World Models Experiments☆649Updated 2 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆397Updated last year
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆571Updated 2 years ago
- Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"☆320Updated 3 years ago
- A simple and highly efficient RTS-game-inspired environment for reinforcement learning☆311Updated 11 months ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆735Updated 5 months ago
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆250Updated 3 years ago
- Multi Agent Reinforcement Learning using MalmÖ☆257Updated 5 years ago
- World Models☆451Updated 4 years ago
- [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning☆1,439Updated 2 years ago
- PlayGround: AI Research into Multi-Agent Learning.☆772Updated last year
- Minecraft environment for Open AI Gym, based on Microsoft's Malmo.☆282Updated 4 years ago
- A customizable framework to create maze and gridworld environments☆266Updated 6 years ago
- Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.☆558Updated 4 years ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆686Updated last year
- Reinforcement Learning with Deep Energy-Based Policies☆425Updated last year
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,523Updated last year
- Repo for reproduction of sequential social dilemmas☆403Updated 3 months ago
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning☆437Updated 6 years ago
- Code release for Learning with Opponent-Learning Awareness and variations.☆148Updated 2 years ago
- Implementation of TRPO and related algorithms☆632Updated 7 years ago
- ☆303Updated 2 years ago
- Trust Region Policy Optimization with TensorFlow and OpenAI Gym☆361Updated 5 years ago
- A PyTorch Platform for Distributed RL☆747Updated 3 years ago