google-deepmind / ai-safety-gridworlds
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
☆611Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ai-safety-gridworlds
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning ag…☆659Updated 5 years ago
- Code for the paper "Emergent Complexity via Multi-agent Competition"☆808Updated last year
- hanabi_learning_environment is a research platform for Hanabi experiments.☆646Updated last year
- Code for the paper "Meta-Learning Shared Hierarchies"☆614Updated last year
- Multi Agent Reinforcement Learning using MalmÖ☆246Updated 4 years ago
- Minecraft environment for Open AI Gym, based on Microsoft's Malmo.☆277Updated 3 years ago
- A customizable framework to create maze and gridworld environments☆260Updated 5 years ago
- World Models Experiments☆624Updated 2 years ago
- PlayGround: AI Research into Multi-Agent Learning.☆767Updated 11 months ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆394Updated last year
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆987Updated 5 years ago
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆558Updated last year
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆703Updated 3 weeks ago
- Code for the paper "Large-Scale Study of Curiosity-Driven Learning"☆804Updated 3 years ago
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆242Updated 2 years ago
- Repo for reproduction of sequential social dilemmas☆387Updated 5 months ago
- Reproduction of OpenAI and DeepMind's "Deep Reinforcement Learning from Human Preferences"☆307Updated 2 years ago
- Code for the paper "Exploration by Random Network Distillation"☆881Updated 4 years ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆654Updated 6 months ago
- Spriteworld: a flexible, configurable python-based reinforcement learning environment☆368Updated 4 years ago
- Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.☆396Updated last year
- A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface☆372Updated last year
- [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning☆1,419Updated last year
- Tools for accelerating safe exploration research.☆506Updated last year
- A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.☆354Updated last year
- A simple framework for experimenting with Reinforcement Learning in Python.☆272Updated 8 months ago
- World Models☆435Updated 4 years ago
- A reinforcement learning framework☆154Updated 5 years ago
- StarCraft II / PySC2 Deep Reinforcement Learning Agents (A2C)☆134Updated 6 years ago
- Code for the paper "Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments"☆302Updated last year