5 papers
Distributions as Actions: A Unified Framework for Diverse Action Spaces
Jiamin He, A. Rupam Mahmood, Martha White
We introduce a novel reinforcement learning (RL) framework that treats parameterized action distributions as actions, redefining the boundary between agent and environment. This re…
InTraGen: Trajectory-controlled Video Generation for Object Interactions
Zuhao Liu, Aleksandar Yanev, Ahmad Mahmood +7
Advances in video generation have significantly improved the realism and quality of created scenes. This has fueled interest in developing intuitive tools that let users leverage v…
Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning
Fahim Shahriar, Cheryl Wang, Alireza Azimi +6
Goal-conditioned reinforcement learning (GCRL) offers a unified way to pursue diverse tasks, yet most existing methods rely on state- or position-based goal representations that ar…
Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers
Gautham Vasan, Mohamed Elsayed, Alireza Azimi +5
Modern deep policy gradient methods achieve effective performance on simulated robotic tasks, but they all require large replay buffers or expensive batch updates, or both, making…
VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding
Ahmad Mahmood, Ashmal Vayani, Muzammal Naseer +2
Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particula…