71 citations · 291 across the 21 of their papers we have counts for
24 papers
CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight
Chensheng Peng, Wenhao Ding, Ran Tian +9
World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such train…
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
Damiano Da Col, Maximilian Igl, Peter Karkus +5
As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important across physical AI domains such as autonomous driving. End-to-end dr…
Planning-aligned Token Compression for Long-Context Autonomous Driving
Zhixuan Liang, Yuxiao Chen, Yurong You +12
Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed real-time computationa…
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
Daniel Dauner, Valentin Charraut, Bastian Berle +10
The pursuit of autonomous driving has produced one of the richest sensor data collections in all of robotics. However, its scale and diversity remain largely untapped. Each dataset…
LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Long Nguyen, Micha Fauth, Bernhard Jaeger +4
Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance. Motivated by this…
RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies
Guillermo Garcia-Cobo, Maximilian Igl, Peter Karkus +5
Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed…
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Jiawei Yang, Jiahui Huang, Yuxiao Chen +10
We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often…
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…
Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning
Zhiyu Huang, Xinshuo Weng, Maximilian Igl +5
Autonomous driving necessitates the ability to reason about future interactions between traffic agents and to make informed evaluations for planning. This paper introduces the \tex…
Hierarchical Imitation Learning for Stochastic Environments
Maximilian Igl, Punit Shah, Paul Mougin +5
Many applications of imitation learning require the agent to generate the full distribution of behaviour observed in the training data. For example, to evaluate the safety of auton…
Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving
Angad Singh, Omar Makhlouf, Maximilian Igl +3
Multi-object state estimation is a fundamental problem for robotic applications where a robot must interact with other moving objects. Typically, other objects' relevant state feat…
Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation
Maximilian Igl, Daewoo Kim, Alex Kuefler +7
Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such car…
Communicating via Markov Decision Processes
Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl +6
We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes…
Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
Charlie Blake, Vitaly Kurin, Maximilian Igl +1
Recent research has shown that graph neural networks (GNNs) can learn policies for locomotion control that are as effective as a typical multi-layer perceptron (MLP), with superior…
My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control
Vitaly Kurin, Maximilian Igl, Tim Rocktäschel +2
Multitask Reinforcement Learning is a promising way to obtain models with better performance, generalisation, data efficiency, and robustness. Most existing work is limited to comp…
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
Luisa Zintgraf, Leo Feng, Cong Lu +4
To rapidly learn a new task, it is often essential for agents to explore efficiently -- especially when performance matters from the first timestep. One way to learn such behaviour…
Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning
Maximilian Igl, Gregory Farquhar, Jelena Luketina +2
Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-station…
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li +4
The ability for policies to generalize to new environments is key to the broad application of RL agents. A promising approach to prevent an agent's policy from overfitting to a lim…
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl +4
Trading off exploration and exploitation in an unknown environment is key to maximising expected return during learning. A Bayes-optimal policy, which does so optimally, conditions…
Multitask Soft Option Learning
Maximilian Igl, Andrew Gambardella, Jinke He +4
We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational…
Deep Variational Reinforcement Learning for POMDPs
Maximilian Igl, Luisa Zintgraf, Tuan Anh Le +2
Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinfo…
Tighter Variational Bounds are Not Necessarily Better
Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le +4
We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the si…
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
Gregory Farquhar, Tim Rocktäschel, Maximilian Igl +1
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has p…
Auto-Encoding Sequential Monte Carlo
Tuan Anh Le, Maximilian Igl, Tom Rainforth +2
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad fam…