lava-lab Goto Github PK

atm

Repository containing code for ICAPS-paper "Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring"

cmarl-verification

cool-mc

The interface between Model Checking and Reinforcement Learning.

dynabs

Controller synthesis for uncertain dynamical systems via formal abstractions

dynabs-jax

fba

improved_spi

lava-lab.github.io

luiaard

Code for the paper "Robust Anytime Learning of Markov Decision Processes"

many-agent-planning

Repository containing the code accompanying the AAAI-24 paper on Many-Agent POMDPs.

mc_pia

pogym

Partially observable environments for reinforcement learning

prmc-sensitivity

ratm

Repository containing code for AAAI 2024 paper "Robust Active Measuring in Uncertain Environments"

safe-slac

Safe SLAC, an algorithm for safe cost-constrained reinforcement learning in high-dimensional POMDPs.

slurf

Sampling-Based Verification of CTMCs with Uncertain Rates

spi_pomdp

Code for the paper "Safe Policy Improvement for POMDPs via Finite-State Controllers"