arXiv subjects

Ehsan Futuhi

Publications and source records attributed to Ehsan Futuhi.

5 recordsLinked to original sources

arXiv2026

Planning with Transformers: Chain of Computation and Structured Context Windows

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 problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leveraging its strength as a pattern-matching system. The COC uses a Structured Context Window (SCW) which provides a constant-sized context window with support for choosing which window is used at each planning step. Within this architecture, the LM is able to learn a planning policy, predicts the world model, and performs the arithmetic operations required during planning. We show that, when given an append-only SCW (resembling a Turing Machine tape), even relatively small LMs trained from scratch can learn planning policies and generalize from a small number of training instances within each planning domain, achieving success rates above 99.89\% on BlocksWorld and the Pancake puzzle. Our analysis of failure cases in Tower of Hanoi (TOH) reveals that they arise from arithmetic operations or from encountering previously unseen tokens. We show that COC can solve TOH problem instances with up to 20 disks, requiring over 1 million actions, while requiring substantially less training data by either (1) planning with symbolical support for arithmetic or by (2) using a deterministic pushdown automaton (PDA) formulation for the SCW.

cs.LG↗

arXiv2025

A Parallel CPU-GPU Framework for Batching Heuristic Operations in Depth-First Heuristic Search

The rapid advancement of GPU technology has unlocked powerful parallel processing capabilities, creating new opportunities to enhance classic search algorithms. This hardware has been exploited in best-first search algorithms with neural network-based heuristics by creating batched versions of A* and Weighted A* that delay heuristic evaluation until sufficiently many states can be evaluated in parallel on the GPU. But, research has not addressed how depth-first algorithms like IDA* or Budgeted Tree Search (BTS) can have their heuristic computations batched. This is more complicated in a tree search, because progress in the search tree is blocked until heuristic evaluations are complete. In this paper we show that GPU parallelization of heuristics can be effectively performed when the tree search is parallelized on the CPU while heuristic evaluations are parallelized on the GPU. We develop a parallelized cost-bounded depth-first search (CB-DFS) framework that can be applied to both IDA* and BTS, significantly improving their performance. We demonstrate the strength of the approach on the 3x3 Rubik's Cube and the 4x4 sliding tile puzzle (STP) with both classifier-based and regression-based heuristics.

cs.AI↗

arXiv2025

Learning Admissible Heuristics for A*: Theory and Practice

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 - guarantees solution optimality. Recent deep learning approaches often disregard admissibility and provide limited guarantees on generalization beyond the training data. This paper addresses both of these limitations. First, we pose heuristic learning as a constrained optimization problem and introduce Cross-Entropy Admissibility (CEA), a loss function that enforces admissibility during training. On the Rubik's Cube domain, this method yields near-admissible heuristics with significantly stronger guidance than compressed pattern database (PDB) heuristics. Theoretically, we study the sample complexity of learning heuristics. By leveraging PDB abstractions and the structural properties of graphs such as the Rubik's Cube, we tighten the bound on the number of training samples needed for A-star to generalize. Replacing a general hypothesis class with a ReLU neural network gives bounds that depend primarily on the network's width and depth, rather than on graph size. Using the same network, we also provide the first generalization guarantees for goal-dependent heuristics.

cs.LG↗

arXiv2024

ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control

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{${\epsilon}{t}$-greedy}, which generates exploratory options for exploring less-visited states. We prove that search using $\epsilon t$-greedy has polynomial sample complexity under mild MDP assumptions. To more efficiently use the information provided by rewarded transitions, we develop a new dual experience replay buffer framework, \emph{GDRB}, and implement \emph{longest n-step returns}. The resulting algorithm, \emph{ETGL-DDPG}, integrates all three techniques: \bm{$\epsilon t$}-greedy, \textbf{G}DRB, and \textbf{L}ongest $n$-step, into DDPG. We evaluate ETGL-DDPG on standard benchmarks and demonstrate that it outperforms DDPG, as well as other state-of-the-art methods, across all tested sparse-reward continuous environments. Ablation studies further highlight how each strategy individually enhances the performance of DDPG in this setting.

cs.LG↗

arXiv2021

On Distributed Algorithms for Minimum Dominating Set problem, from theory to application

In this paper, we propose a distributed algorithm for the minimum dominating set problem. For some especial networks, we prove theoretically that the achieved answer by our proposed algorithm is a constant approximation factor of the exact answer. This problem arises naturally in social networks, for example in news spreading, avoiding rumor spreading and recommendation spreading. So we implement our algorithm on massive social networks and compare our results with the state of the art algorithms. Also, we extend our algorithm to solve the $k$-distance dominating set problem and experimentally study the efficiency of the proposed algorithm. Our proposed algorithm is fast and easy to implement and can be used in dynamic networks where the edges and vertices are added or deleted constantly. More importantly, based on the experimental results the proposed algorithm has reasonable solutions and running time which enables us to use it in distributed model practically.

cs.DC↗