34 citations · 135 across the 25 of their papers we have counts for
10 papers · 1 filter
Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
Zhejun Zhang, Peter Karkus, Maximilian Igl +4
Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop, faithfully recovers the joint distribution of trajectories observed in the real wor…
Learning Multiple Initial Solutions to Optimization Problems
Elad Sharony, Heng Yang, Tong Che +3
Sequentially solving similar optimization problems under strict runtime constraints is essential for many applications, such as robot control, autonomous driving, and portfolio man…
Foundation Models for Semantic Novelty in Reinforcement Learning
Tarun Gupta, Peter Karkus, Tong Che +2
Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model,…
Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
Filippos Christianos, Peter Karkus, Boris Ivanovic +2
Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predictin…
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Peter Karkus, Mehdi Mirza, Arthur Guez +5
Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control. Tabula rasa deep reinforcement learning (RL)…
Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations
Xiao Ma, Peter Karkus, David Hsu +2
Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with part…
Differentiable Algorithm Networks for Composable Robot Learning
Peter Karkus, Xiao Ma, David Hsu +3
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a…
Particle Filter Recurrent Neural Networks
Xiao Ma, Peter Karkus, David Hsu +1
Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data. To tackle highly variable and noisy real-world data, we introduce Particl…
Factored Contextual Policy Search with Bayesian Optimization
Robert Pinsler, Peter Karkus, Andras Kupcsik +2
Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy…
Factored Contextual Policy Search with Bayesian Optimization
Peter Karkus, Andras Kupcsik, David Hsu +1
Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimizatio…