5 citations · 11 across the 13 of their papers we have counts for
14 papers
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
Lior Cohen, Ofir Nabati, Kaixin Wang +2
We study diffusion-based world models for reinforcement learning, which offer high generative fidelity but face critical efficiency challenges in control. Current methods either re…
Investigating mixed traffic dynamics of pedestrians and non-motorized vehicles at urban intersections: Observation experiments and modelling
Chaojia Yu, Kaixin Wang, Junle Li +1
Urban intersections with mixed pedestrian and non-motorized vehicle traffic present complex safety challenges, yet traditional models fail to account for dynamic interactions arisi…
TurboReg: TurboClique for Robust and Efficient Point Cloud Registration
Shaocheng Yan, Pengcheng Shi, Zhenjun Zhao +4
Robust estimation is essential in correspondence-based Point Cloud Registration (PCR). Existing methods using maximal clique search in compatibility graphs achieve high recall but…
Social Networks: Enumerating Maximal Community Patterns in -Closed Graphs
Gabriela Bourla, Kaixin Wang, Fan Wei +1
Jacob Fox, C. Seshadhri, Tim Roughgarden, Fan Wei, and Nicole Wein introduced the model of -closed graphs--a distribution-free model motivated by triadic closure, one of the mos…
Simulus: Combining Improvements in Sample-Efficient World Model Agents
Lior Cohen, Kaixin Wang, Bingyi Kang +2
World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expe…
Arborescences of Random Covering Graphs
Muchen Ju, Junjie Ni, Kaixin Wang +1
A rooted arborescence of a directed graph is a spanning tree directed towards a particular vertex. A recent work of Chepuri et al. showed that the arborescences of a covering graph…
How Far is Video Generation from World Model: A Physical Law Perspective
Bingyi Kang, Yang Yue, Rui Lu +5
OpenAI's Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws. However, the ability of video generation models to…
Improving Token-Based World Models with Parallel Observation Prediction
Lior Cohen, Kaixin Wang, Bingyi Kang +1
Motivated by the success of Transformers when applied to sequences of discrete symbols, token-based world models (TBWMs) were recently proposed as sample-efficient methods. In TBWM…
Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
Kaixin Wang, Uri Gadot, Navdeep Kumar +2
Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, current RMDP methods…
An Efficient Solution to s-Rectangular Robust Markov Decision Processes
Navdeep Kumar, Kfir Levy, Kaixin Wang +1
We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs wh…
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
Fengzhuo Zhang, Boyi Liu, Kaixin Wang +3
The cooperative Multi-A gent R einforcement Learning (MARL) with permutation invariant agents framework has achieved tremendous empirical successes in real-world applications. Unfo…
Policy Gradient for Reinforcement Learning with General Utilities
Navdeep Kumar, Kaixin Wang, Kfir Levy +1
In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a p…
Efficient Policy Iteration for Robust Markov Decision Processes via Regularization
Navdeep Kumar, Kfir Levy, Kaixin Wang +1
Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for…
The Geometry of Robust Value Functions
Kaixin Wang, Navdeep Kumar, Kuangqi Zhou +3
The space of value functions is a fundamental concept in reinforcement learning. Characterizing its geometric properties may provide insights for optimization and representation. E…