Search Results - "Shperberg, Shahaf"

Adaptive Curriculum Learning With Successor Features for Imbalanced Compositional Reward Functions by Szoke, Laszlo, Shperberg, Shahaf S., Holtz, Jarrett, Allievi, Alessandro

“…This work addresses the challenge of reinforcement learning with reward functions that feature highly imbalanced components in terms of importance and scale…”
Get full text

Some Properties of Batch Value of Information in the Selection Problem by Shperberg, Shahaf S., Shimony, Solomon Eyal

“…Given a set of items of unknown utility, we need to select one with a utility as high as possible (“the selection problem”). Measurements (possibly noisy) of…”
Get full text

Conflict-tolerant and conflict-free multi-agent meeting by Atzmon, Dor, Felner, Ariel, Li, Jiaoyang, Shperberg, Shahaf, Sturtevant, Nathan, Koenig, Sven

“…In the Multi-Agent Meeting problem (MAM), the task is to find the optimal meeting location for multiple agents, as well as a path for each agent to that…”
Get full text

A collective AI via lifelong learning and sharing at the edge by Soltoggio, Andrea, Ben-Iwhiwhu, Eseoghene, Braverman, Vladimir, Eaton, Eric, Epstein, Benjamin, Ge, Yunhao, Halperin, Lucy, How, Jonathan, Itti, Laurent, Jacobs, Michael A., Kantharaju, Pavan, Le, Long, Lee, Steven, Liu, Xinran, Monteiro, Sildomar T., Musliner, David, Nath, Saptarshi, Panda, Priyadarshini, Peridis, Christos, Pirsiavash, Hamed, Parekh, Vishwa, Roy, Kaushik, Shperberg, Shahaf, Siegelmann, Hava T., Stone, Peter, Vedder, Kyle, Wu, Jingfeng, Yang, Lin, Zheng, Guangyao, Kolouri, Soheil

“…One vision of a future artificial intelligence (AI) is where many separate units can learn independently over a lifetime and share their knowledge with each…”
Get full text

Effort Allocation for Deadline-Aware Task and Motion Planning: A Metareasoning Approach by Sung, Yoonchang, Shperberg, Shahaf S, Wang, Qi, Stone, Peter

“…In robot planning, tasks can often be achieved through multiple options, each consisting of several actions. This work specifically addresses deadline…”
Get full text

Enhancing Numeric-SAM for Learning with Few Observations by Mordoch, Argaman, Shperberg, Shahaf S, Stern, Roni, Juba, Berndan

“…A significant challenge in applying planning technology to real-world problems lies in obtaining a planning model that accurately represents the problem's…”
Get full text

Learning a Shield from Catastrophic Action Effects: Never Repeat the Same Mistake by Shperberg, Shahaf S, Liu, Bo, Stone, Peter

“…Agents that operate in an unknown environment are bound to make mistakes while learning, including, at least occasionally, some that lead to catastrophic…”
Get full text

Planning and Acting While the Clock Ticks by Coles, Andrew, Karpas, Erez, Lavrinenko, Andrey, Ruml, Wheeler, Shimony, Solomon Eyal, Shperberg, Shahaf

“…Standard temporal planning assumes that planning takes place offline and then execution starts at time 0. Recently, situated temporal planning was introduced,…”
Get full text

A Formal Metareasoning Model of Concurrent Planning and Execution by Elboher, Amihay, Bensoussan, Ava, Karpas, Erez, Ruml, Wheeler, Shperberg, Shahaf S, Shimony, Solomon E

“…Agents that plan and act in the real world must deal with the fact that time passes as they are planning. When timing is tight, there may be insufficient time…”
Get full text