This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
☆634May 18, 2022Updated 4 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning ag…☆666Sep 6, 2019Updated 6 years ago
- Training (hopefully) safe agents in gridworlds☆26May 12, 2019Updated 7 years ago
- Tools for accelerating safe exploration research.☆600Apr 2, 2023Updated 3 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,475Jun 24, 2026Updated 2 weeks ago
- Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.☆462Apr 2, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,551Mar 30, 2026Updated 3 months ago
- Inferring beliefs about dynamics from behavior☆30May 24, 2018Updated 8 years ago
- Safe reinforcement learning with stability guarantees☆238Feb 8, 2022Updated 4 years ago
- Safe Reinforcement Learning algorithms☆75Aug 27, 2022Updated 3 years ago
- rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.☆3,069Jun 10, 2023Updated 3 years ago
- Code for the paper "Emergent Complexity via Multi-agent Competition"☆835Apr 2, 2023Updated 3 years ago
- Leave No Trace is an algorithm for safe reinforcement learning.☆15Apr 30, 2018Updated 8 years ago
- Reinforcement Learning in PyTorch☆2,279Jan 4, 2021Updated 5 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆406Oct 7, 2023Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- SafeLife: safety benchmarks for reinforcement learning agents☆61May 13, 2021Updated 5 years ago
- [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning☆1,480Dec 7, 2022Updated 3 years ago
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆1,026Mar 13, 2019Updated 7 years ago
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆49Apr 1, 2022Updated 4 years ago
- Code for "Unsupervised State Representation Learning in Atari"☆259Nov 2, 2023Updated 2 years ago
- Code for SPIBB-DQN and Soft-SPIBB-DQN☆11May 5, 2020Updated 6 years ago
- A gym interface for AI safety gridworlds created in pycolab.☆18May 12, 2022Updated 4 years ago
- ☆12Aug 24, 2018Updated 7 years ago
- TensorFlow Reinforcement Learning☆3,133Dec 8, 2022Updated 3 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A customizable framework to create maze and gridworld environments☆271Apr 5, 2019Updated 7 years ago
- NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark☆569Jun 19, 2026Updated 2 weeks ago
- A customisable 2D platform for agent-based AI research☆441Oct 5, 2023Updated 2 years ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆772Mar 2, 2026Updated 4 months ago
- Reinforcement Learning with Deep Energy-Based Policies☆438Nov 28, 2023Updated 2 years ago
- OpenAI Baselines: high-quality implementations of reinforcement learning algorithms☆16,739Aug 1, 2024Updated last year
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆725May 12, 2024Updated 2 years ago
- A customisable 3D platform for agent-based AI research☆7,365Jan 4, 2023Updated 3 years ago
- Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.☆880Oct 16, 2021Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Using RLLib and PycoLab to explore intelligent cooperative behavior in sequential social dilemmas☆54Dec 8, 2022Updated 3 years ago
- Constrained Exploration and Recovery from Experience Shaping☆22Apr 18, 2019Updated 7 years ago
- A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release th…☆205May 25, 2020Updated 6 years ago
- Learning Latent Dynamics for Planning from Pixels☆1,257Mar 24, 2023Updated 3 years ago
- Reward Learning by Simulating the Past☆46May 9, 2019Updated 7 years ago
- A Python interface for reinforcement learning environments☆401Dec 23, 2022Updated 3 years ago
- Code for human intervention reinforcement learning☆35Jan 8, 2018Updated 8 years ago