4 papers
Planning with Transformers: Chain of Computation and Structured Context Windows
Ehsan Futuhi, Nathan R. Sturtevant
Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning pr…
Learning Admissible Heuristics for A*: Theory and Practice
Ehsan Futuhi, Nathan R. Sturtevant
Heuristic functions are central to the performance of search algorithms such as A-star, where admissibility - the property of never overestimating the true shortest-path cost - gua…
ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control
Ehsan Futuhi, Shayan Karimi, Chao Gao +1
We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{$…
A Parallel CPU-GPU Framework for Batching Heuristic Operations in Depth-First Heuristic Search
Ehsan Futuhi, Nathan R. Sturtevant
The rapid advancement of GPU technology has unlocked powerful parallel processing capabilities, creating new opportunities to enhance classic search algorithms. This hardware has b…