8 citations · 10 across the 11 of their papers we have counts for
11 papers
Dynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning
Fahim Shahriar, Cheryl Wang, Alireza Azimi +5
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…
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…
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…
Streaming Deep Reinforcement Learning Finally Works
Mohamed Elsayed, Gautham Vasan, Elena Sorina Lupu +1
Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streaming learning has remained a persis…
Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
Gautham Vasan, Yan Wang, Fahim Shahriar +3
Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems,…
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…
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
Bram Grooten, Tristan Tomilin, Gautham Vasan +5
The visual world provides an abundance of information, but many input pixels received by agents often contain distracting stimuli. Autonomous agents need the ability to distinguish…
SmartControllerJS: A JavaScript library to turn smartphones into controllers for web-based interactive experiments
Emma Poliakova, Fraser Dempster, Abubakr Mahmood +1
We introduce SmartControllerJS, a new JavaScript library for fast, cost-effective designing of web applications controlled via everyday smartphones. At its core, SmartControllerJS…
Heteroscedastic Uncertainty for Robust Generative Latent Dynamics
Oliver Limoyo, Bryan Chan, Filip Marić +3
Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The proble…
Autoregressive Policies for Continuous Control Deep Reinforcement Learning
Dmytro Korenkevych, A. Rupam Mahmood, Gautham Vasan +1
Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies…