LAS @ ETH Zurich

aceirl

Implementation of "Active Exploration for Inverse Reinforcement Learning (AceIRL), NeurIPS 2022.

adaga

adaptive-constraint-learning

Code accompanying the paper "Interactively Learning Preference Constraints in Linear Bandits" (ICML 2022).

GNNBO

Code for our paper "Graph Neural Network Bandits"

gosafeopt

Globally Safe Model-free Exploration of Dynamical Systems

jax-cpo

Implementation of Constrained Policy Optimization with JAX

model-based-meta-rl

Model-based-policy-optimizers

Model based policy optimizers

model-based-rl

Repository for doing model based RL

opax

lasgroup/gosafeopt

Globally Safe Model-free Exploration of Dynamical Systems

lasgroup/opax

lasgroup/model-based-meta-rl

lasgroup/aceirl

Implementation of "Active Exploration for Inverse Reinforcement Learning (AceIRL), NeurIPS 2022.

lasgroup/adaptive-constraint-learning

Code accompanying the paper "Interactively Learning Preference Constraints in Linear Bandits" (ICML 2022).

lasgroup/model-based-rl

Repository for doing model based RL

lasgroup/adaga

lasgroup/bayesian_statistical_models

lasgroup/GNNBO

Code for our paper "Graph Neural Network Bandits"

lasgroup/jax-cpo

Implementation of Constrained Policy Optimization with JAX

lasgroup/Model-based-policy-optimizers

Model based policy optimizers

lasgroup/cocorl

Code for Convex Constraint Learning for RL

lasgroup/lbsgd-rl

Implementation of Log Barriers SGD used in the RL experiment of the "Log Barriers for Safe Optimization of Smooth Objectives and Constraints with Application to Reinforcement Learning" paper.

lasgroup/ALEXP

Simultaneous Online Optimization and Model Selection, based on our paper "Anytime Model Selection for Linear Bandits"

lasgroup/ml-protein-design-sav-gold

analysis, preparation and reporting for streptavidin design using active learning

lasgroup/safe-adaptation-agents

Implementation of adaptive constrained RL algorithms. Child repository of @lasgroup/safe-adaptation-gym

lasgroup/simulation_transfer

Transferring inductive bias / prior knowledge from domain specific simulations and models

lasgroup/HPGD

lasgroup/MaxMinLCB

Code for our paper "Bandits with Preference Feedback: A Stackelberg Game Perspective"

lasgroup/ODIN

Python 3.6 and TensorFlow implementation of the ODIN algorithm

lasgroup/TaCoS

lasgroup/ushcn_dgm

lasgroup/AReS-MaRS

Python 3.6 and TensorFlow implementation of the AReS and MaRS algorithms

lasgroup/dgm

lasgroup/FGPGM

lasgroup/safe-adaptation-gym

A Safety-Gym based benchmark suite for safe meta RL

lasgroup/stable-ndde