Georg Martius

21

Papers

20

Total Citations

Papers (21)

Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling

Active Fine-Tuning of Multi-Task Policies

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

Advancing Out-of-Distribution Detection via Local Neuroplasticity

Temporally Consistent Object-Centric Learning by Contrasting Slots

Forecasting in Offline Reinforcement Learning for Non-stationary Environments

NeurIPS 2025arXiv

Causal Action Influence Aware Counterfactual Data Augmentation

Learning with 3D rotations, a hitchhiker's guide to SO(3)

LPGD: A General Framework for Backpropagation through Embedded Optimization Layers

Modelling Microbial Communities with Graph Neural Networks

Optimizing Rank-Based Metrics With Blackbox Differentiation

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

NeurIPS 2021arXiv

Hierarchical Reinforcement Learning with Timed Subgoals

NeurIPS 2021arXiv

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

NeurIPS 2021arXiv

Planning from Pixels in Environments with Combinatorially Hard Search Spaces

NeurIPS 2021arXiv

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

NeurIPS 2022arXiv

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

NeurIPS 2022arXiv

Goal-conditioned Offline Planning from Curious Exploration

NeurIPS 2023arXiv

Online Learning under Adversarial Nonlinear Constraints

NeurIPS 2023arXiv

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

NeurIPS 2023arXiv

Regularity as Intrinsic Reward for Free Play

NeurIPS 2023arXiv