martius-lab/rair-mbrl

Stars
1
Language
Jupyter Notebook
License
MIT License
Created 11 months ago
Updated 11 months ago

martius-lab/rair-mbrl

martius-lab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Code for our NeurIPS 2023 Paper: Regularity as Intrinsic Reward for Free Play

blackbox-backprop

Torch modules that wrap blackbox combinatorial solvers according to the method presented in "Differentiating Blackbox Combinatorial Solvers"

hitchhiking-rotations

Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024

l4-optimizer

Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"

Jupyter Notebook

blackbox-deep-graph-matching

Repository for our paper: Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

CombOptNet

Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

iCEM

improved Cross Entropy Method for trajectory optimization

EQL

Equation Learner, a neural network approach to symbolic regression

Jupyter Notebook

wasabi

Repository for our paper: Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations Proceedings of the 6th Conference on Robot Learning (CoRL),

depRL

Repository for our ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

cid-in-rl

Code for the paper: "Causal Influence Detection for Improving Efficiency in Reinforcement Learning", by Seitzer, M., Schölkopf, B., Martius, G., NeurIPS 2021

pink-noise-rl

beta-nll

beta-NLL introduced in our paper "On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks" ICLR 2022

EQL_Tensorflow

Tensorflow implementation of equation learner

cassi

Repository for our paper: Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions. (ICRA 2023)

HiTS

Code for the paper: Hierarchical Reinforcement Learning With Timed Subgoals, published at NeurIPS 2021

GateL0RD

Code for our NeurIPS 2021 paper: Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

SMORL

blackbox-differentiation-combinatorial-solvers

Jupyter Notebook

dominic

Code for our ICRA 2024 paper on learning diverse skills

AL4MyoChallenge

Code for the submission of the team AL4Muscles to the MyoChallenge 2022

videosaur

Repository for our paper "Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities"

laser-hockey-env

A simple laser-hockey gym environment for RL agents

PPGS

Planning from Pixels in Environments with Combinatorially Hard Search Spaces -- NeurIPS 2021

cee-us

Repository for the paper: "Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation" @ NeurIPS 2022

Jupyter Notebook

learningwithmuscles

Repo for the paper: Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks. https://al.is.mpg.de/publications/wochneretal22

cluster_utils

solver-differentiation-identity

Repository for the code of our ICLR paper: Backpropagation through Combinatorial Algorithms: Identity with Projection Works

Jupyter Notebook

caiac

Code for the paper: Causal Action Influence Aware Counterfactual Data Augmentation @ICML2024

GateL0RD-paper

Code for the paper: Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

EQL-Pytorch

Equation learning method -- pytorch implementation

Minsight-sensor

Code for the Minsight vision-based haptic sensor

Jupyter Notebook

puzzlegen

Combinatorially Hard Games where the levels are procedurally generated

L0-regularization

A TensorFlow implementation of L0 regularization (Louizos et al 2017)

Jupyter Notebook

teamproject-competition-server

A competition server for running 2-player game competitions

smart-settings

A nifty little wrapper around settings files for python

dynamic-rl-benchmarks

Benchmark tasks proposed in "Hierarchical reinforcement learning with Timed Subgoals" by Guertler, Buechler and Martius

APEX

Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory Optimizers, ICLR 2021

gcopfce

Repository for our NeurIPS 2023 paper on Goal-conditioned Offline Planning from Curious Exploration