5 papers
Constrained Group Relative Policy Optimization
Roger Girgis, Rodrigue de Schaetzen, Luke Rowe +3
Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with constrained policy optimization (e.g.…
Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving
Luke Rowe, Rodrigue de Schaetzen, Roger Girgis +2
Maintaining good driving behavior in out-of-distribution scenarios remains a critical challenge in autonomous driving. A promising direction is to leverage the generalist knowledge…
Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
Anthony Gosselin, Ge Ya Luo, Luis Lara +5
Video diffusion techniques have advanced significantly in recent years; however, they struggle to generate realistic imagery of car crashes due to the scarcity of accident events i…
Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
Luke Rowe, Roger Girgis, Anthony Gosselin +3
We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and…
CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning
Luke Rowe, Roger Girgis, Anthony Gosselin +5
Evaluating autonomous vehicle stacks (AVs) in simulation typically involves replaying driving logs from real-world recorded traffic. However, agents replayed from offline data are…