Blending Data-Driven Priors in Dynamic Games
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929412403888128 |
|---|---|
| author | Lidard, Justin Hu, Haimin Hancock, Asher Zhang, Zixu Contreras, Albert Gimó Modi, Vikash DeCastro, Jonathan Gopinath, Deepak Rosman, Guy Leonard, Naomi Ehrich Santos, María Fisac, Jaime Fernández |
| author_facet | Lidard, Justin Hu, Haimin Hancock, Asher Zhang, Zixu Contreras, Albert Gimó Modi, Vikash DeCastro, Jonathan Gopinath, Deepak Rosman, Guy Leonard, Naomi Ehrich Santos, María Fisac, Jaime Fernández |
| contents | As intelligent robots like autonomous vehicles become increasingly deployed in the presence of people, the extent to which these systems should leverage model-based game-theoretic planners versus data-driven policies for safe, interaction-aware motion planning remains an open question. Existing dynamic game formulations assume all agents are task-driven and behave optimally. However, in reality, humans tend to deviate from the decisions prescribed by these models, and their behavior is better approximated under a noisy-rational paradigm. In this work, we investigate a principled methodology to blend a data-driven reference policy with an optimization-based game-theoretic policy. We formulate KLGame, an algorithm for solving non-cooperative dynamic game with Kullback-Leibler (KL) regularization with respect to a general, stochastic, and possibly multi-modal reference policy. Our method incorporates, for each decision maker, a tunable parameter that permits modulation between task-driven and data-driven behaviors. We propose an efficient algorithm for computing multi-modal approximate feedback Nash equilibrium strategies of KLGame in real time. Through a series of simulated and real-world autonomous driving scenarios, we demonstrate that KLGame policies can more effectively incorporate guidance from the reference policy and account for noisily-rational human behaviors versus non-regularized baselines. Website with additional information, videos, and code: https://kl-games.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Blending Data-Driven Priors in Dynamic Games Lidard, Justin Hu, Haimin Hancock, Asher Zhang, Zixu Contreras, Albert Gimó Modi, Vikash DeCastro, Jonathan Gopinath, Deepak Rosman, Guy Leonard, Naomi Ehrich Santos, María Fisac, Jaime Fernández Robotics Artificial Intelligence Systems and Control Optimization and Control As intelligent robots like autonomous vehicles become increasingly deployed in the presence of people, the extent to which these systems should leverage model-based game-theoretic planners versus data-driven policies for safe, interaction-aware motion planning remains an open question. Existing dynamic game formulations assume all agents are task-driven and behave optimally. However, in reality, humans tend to deviate from the decisions prescribed by these models, and their behavior is better approximated under a noisy-rational paradigm. In this work, we investigate a principled methodology to blend a data-driven reference policy with an optimization-based game-theoretic policy. We formulate KLGame, an algorithm for solving non-cooperative dynamic game with Kullback-Leibler (KL) regularization with respect to a general, stochastic, and possibly multi-modal reference policy. Our method incorporates, for each decision maker, a tunable parameter that permits modulation between task-driven and data-driven behaviors. We propose an efficient algorithm for computing multi-modal approximate feedback Nash equilibrium strategies of KLGame in real time. Through a series of simulated and real-world autonomous driving scenarios, we demonstrate that KLGame policies can more effectively incorporate guidance from the reference policy and account for noisily-rational human behaviors versus non-regularized baselines. Website with additional information, videos, and code: https://kl-games.github.io/. |
| title | Blending Data-Driven Priors in Dynamic Games |
| topic | Robotics Artificial Intelligence Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2402.14174 |