paper-with-me

Papers

Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See

2026-06-23 · Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi, Aissa Boulmerka arxiv

We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios from the Waymo Open Motion Dataset. A central methodological finding is that naïve pooling of timesteps across episodes substantially underestimates the attention$\unicode{x2013}$risk relationship; within-episode correlation with Fisher z-transform aggregation is the appropriate statistic and reveals a robustly positive link between collision risk and agent-directed attention. Building on this validated methodology, we demonstrate two reward-conditioned effects: agents trained with navigation rewards allocate up to $2.0\times$ more attention to GPS-path tokens than those trained with additional proximity penalties$\unicode{x2014}$and $4.7\times$ more than agents with no navigation incentive$\unicode{x2014}$revealing that reward content directly determines which scene elements the encoder prioritizes, and continuous time-to-collision penalties create a $\textit{learned vigilance prior}$$\unicode{x2014}$elevated resting agent surveillance maintained throughout collision-free phases. In several scenarios, the complete-reward and minimal-reward models exhibit opposite attention$\unicode{x2013}$risk correlation directions, demonstrating that reward design can qualitatively reverse attentional strategy rather than merely modulating its magnitude. These results suggest that attention analysis is a practical diagnostic for verifying that a reward function produces the intended representational behaviour in safety-critical RL systems.

📄 PDF Abstract BibTeX arXiv:2606.25127

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningAutonomous Driving

Similar Papers 제목 키워드 기반

Reward Design for Physical Reasoning in Vision-Language Models

2026-04-15 · Derek Lilienthal, Manisha Mukherjee, Sameera Horawalavithana arxiv

Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even state-of-the-art Vision Language Models (VLMs) fall far short of human p…

Spatial Reasoning

Reward function shape exploration in adversarial imitation learning: an empirical study

2021-04-14 · Yawei Wang, Xiu Li

For adversarial imitation learning algorithms (AILs), no true rewards are obtained from the environment for learning the strategy. However, the pseudo rewards based on the output of the discriminator are still required. …

continuous-controlContinuous ControlImitation LearningMuJoCo

Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation

2026-05-16 · Shuyin Ouyang, Zhaozhi Qian, Faroq AL-Tam, Muhammad AL-Qurishi 외 arxiv

Reinforcement Learning (RL) is an important paradigm for aligning Diffusion Language Models (DLMs) toward functional correctness in code generation. However, these models often encounter a ``capability cliff'' on complex…

Reinforcement LearningCode Generation

Neural Garbage Collection: Learning to Forget while Learning to Reason

2026-04-20 · Michael Y. Li, Jubayer Ibn Hamid, Emily B. Fox, Noah D. Goodman arxiv

Chain-of-thought reasoning has driven striking advances in language model capability, yet every reasoning step grows the KV cache, creating a bottleneck to scaling this paradigm further. Current approaches manage these c…

Reinforcement Learning

BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback

2024-02-04 · Gaurav Pandey, Yatin Nandwani, Tahira Naseem, Mayank Mishra 외

Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same level of attention in reinforcement lear…

Language ModelingLanguage ModellingText Generation