Library
MASA Safe-RL
Modular library for safe RL, providing baselines for a number of constraints using a variety of algorithms.
Software
Software repositories and documentation will appear here. Expect verification toolchains, benchmarks, and example integrations.
Featured
Tool
ProSh
Probabilistic shielding for constrained Markov Decision Processes with unknown safety dynamics.
By year
2026
Library
MASA Safe-RL
Modular library for safe RL, providing baselines for a number of constraints using a variety of algorithms.
Tool
PMAS
Probabilistic shielding for decentralised multiagent RL with dynamics induced through world and opponent modelling.
2025
Tool
GR(1) Shielding
Adaptive shielding using GR(1) specifications and Inductive Logic Programming to repair specifications.
Tool
ProSh
Probabilistic shielding for constrained Markov Decision Processes with unknown safety dynamics.
Tool
Quantitative Reward Monitoring
Write formal Reinforcement Learning reward specifications in Quantitative Linear Temporal Logic on finite traces.
2023
Tool
Approximate Model-Based Shielding
Latent shielding for safe RL, including continuous dynamics using DreamerV3.