google-deepmind / ai-safety-gridworldsView external linksLinks
This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
☆626May 18, 2022Updated 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…☆662Sep 6, 2019Updated 6 years ago
- Tools for accelerating safe exploration research.☆581Apr 2, 2023Updated 2 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,398Dec 15, 2025Updated 2 months ago
- Training (hopefully) safe agents in gridworlds☆25May 12, 2019Updated 6 years ago
- Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.☆456Apr 2, 2023Updated 2 years ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,530Apr 13, 2024Updated last year
- Code for the paper "Emergent Complexity via Multi-agent Competition"☆826Apr 2, 2023Updated 2 years ago
- Inferring beliefs about dynamics from behavior☆30May 24, 2018Updated 7 years ago
- rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.☆3,040Jun 10, 2023Updated 2 years ago
- [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning☆1,471Dec 7, 2022Updated 3 years ago
- Safe reinforcement learning with stability guarantees☆236Feb 8, 2022Updated 4 years ago
- A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.☆1,019Mar 13, 2019Updated 6 years ago
- Reinforcement Learning with Deep Energy-Based Policies☆435Nov 28, 2023Updated 2 years ago
- A customizable framework to create maze and gridworld environments☆269Apr 5, 2019Updated 6 years ago
- Reinforcement Learning in PyTorch☆2,276Jan 4, 2021Updated 5 years ago
- RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code☆715May 12, 2024Updated last year
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆49Apr 1, 2022Updated 3 years ago
- Simple and easily configurable 3D FPS-game-like environments for reinforcement learning☆754Dec 15, 2025Updated 2 months ago
- Safe Reinforcement Learning algorithms☆75Aug 27, 2022Updated 3 years ago
- Learning Latent Dynamics for Planning from Pixels☆1,234Mar 24, 2023Updated 2 years ago
- TensorFlow Reinforcement Learning☆3,135Dec 8, 2022Updated 3 years ago
- Code for the paper "Quantifying Transfer in Reinforcement Learning"☆407Oct 7, 2023Updated 2 years ago
- Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"☆206Nov 22, 2018Updated 7 years ago
- Code for "Unsupervised State Representation Learning in Atari"☆259Nov 2, 2023Updated 2 years ago
- A customisable 2D platform for agent-based AI research☆437Oct 5, 2023Updated 2 years ago
- Constrained Exploration and Recovery from Experience Shaping☆22Apr 18, 2019Updated 6 years ago
- A customisable 3D platform for agent-based AI research☆7,321Jan 4, 2023Updated 3 years ago
- A Python interface for reinforcement learning environments☆391Dec 23, 2022Updated 3 years ago
- Repo containing code for multi-agent deep reinforcement learning (MADRL).☆733Apr 12, 2023Updated 2 years ago
- OpenAI Baselines: high-quality implementations of reinforcement learning algorithms☆16,651Aug 1, 2024Updated last year
- A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release th…☆202May 25, 2020Updated 5 years ago
- Leave No Trace is an algorithm for safe reinforcement learning.☆15Apr 30, 2018Updated 7 years ago
- Implementation of TRPO and related algorithms☆646May 20, 2018Updated 7 years ago
- SafeLife: safety benchmarks for reinforcement learning agents☆61May 13, 2021Updated 4 years ago
- Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.☆876Oct 16, 2021Updated 4 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆705Jul 14, 2020Updated 5 years ago
- An implementation of FeUdal Networks for Hierarchical Reinforcement Learning as published : https://arxiv.org/abs/1703.01161☆186Nov 1, 2017Updated 8 years ago
- Using RLLib and PycoLab to explore intelligent cooperative behavior in sequential social dilemmas☆54Dec 8, 2022Updated 3 years ago
- DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.☆2,166Apr 2, 2023Updated 2 years ago