arXiv subjects

Mohammad Shahid Shaikh

Publications and source records attributed to Mohammad Shahid Shaikh.

7 recordsLinked to original sources

arXiv2026

Embodiment-Induced Coordination Regimes in Tabular Multi-Agent Q-Learning

Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evaluated in settings that confound coordination structure with function approximation and partial observability. We isolate coordination structure in a fully tabular 8x8 predator-prey gridworld with explicit speed and stamina constraints, comparing all four pairings of Independent and Centralized Q-Learning across three kinematic regimes over 10 seeds. Fully independent learning (IQL-IQL) yields shorter episodes and higher predator returns than the fully centralized configuration (CQL-CQL) in every regime and every seed (Wilcoxon p = 0.00195, Cliff's delta = 1.0). Asymmetric IQL-CQL pairings produce coordination breakdowns that persist across the 40,000 episode training budget rather than resolving as transient instability. A best-response test against frozen IQL-IQL predators shows that even the strongest configuration has not converged to equilibrium at 40k episodes, so between-configuration differences reflect learning dynamics under a shared budget rather than end-state performance. We propose a mechanism we call temporal synchronization lock: a shared value function couples all agent decisions, so when one agent is stamina-limited the joint Q-value forces capable partners into suboptimal waits, while independent learners continue asynchronous pursuit. Because this pathology arises from credit assignment rather than function approximation, we conjecture analogous effects may arise in deep MARL methods that centralize credit during training. Centralized coordination is not uniformly beneficial; its advantage over independent learning shrinks or disappears under embodiment constraints, and mixed centralized-independent pairings can perform worse than either uniform choice.

cs.MA↗

arXiv2026

A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer

Transfer learning in deep reinforcement learning is often motivated by improved stability and reduced training cost, but it can also fail under substantial domain shift. This paper presents a controlled empirical study examining how architectural differences between Double Deep Q-Networks (DDQN) and Dueling DQN influence transfer behavior across environments. Using CartPole as a source task and LunarLander as a structurally distinct target task, we evaluate a fixed layer-wise representation transfer protocol under identical hyperparameters and training conditions, with baseline agents trained from scratch used to contextualize transfer effects. Empirical results show that DDQN consistently avoids negative transfer under the examined setup and maintains learning dynamics comparable to baseline performance in the target environment. In contrast, Dueling DQN consistently exhibits negative transfer under identical conditions, characterized by degraded rewards and unstable optimization behavior. Statistical analysis across multiple random seeds confirms a significant performance gap under transfer. These findings suggest that architectural inductive bias is strongly associated with robustness to cross-environment transfer in value-based deep reinforcement learning under the examined transfer protocol.

cs.LG↗

arXiv2025

Bridging the Gap Between Theoretical and Practical Reinforcement Learning in Undergraduate Education

This innovative practice category paper presents an innovative framework for teaching Reinforcement Learning (RL) at the undergraduate level. Recognizing the challenges posed by the complex theoretical foundations of the subject and the need for hands-on algorithmic practice, the proposed approach integrates traditional lectures with interactive lab-based learning. Drawing inspiration from effective pedagogical practices in computer science and engineering, the framework engages students through real-time coding exercises using simulated environments such as OpenAI Gymnasium. The effectiveness of this approach is evaluated through student surveys, instructor feedback, and course performance metrics, demonstrating improvements in understanding, debugging, parameter tuning, and model evaluation. Ultimately, the study provides valuable insight into making Reinforcement Learning more accessible and engaging, thereby equipping students with essential problem-solving skills for real-world applications in Artificial Intelligence.

cs.CY↗

arXiv2014

Document clustering using graph based document representation with constraints

Document clustering is an unsupervised approach in which a large collection of documents (corpus) is subdivided into smaller, meaningful, identifiable, and verifiable sub-groups (clusters). Meaningful representation of documents and implicitly identifying the patterns, on which this separation is performed, is the challenging part of document clustering. We have proposed a document clustering technique using graph based document representation with constraints. A graph data structure can easily capture the non-linear relationships of nodes, document contains various feature terms that can be non-linearly connected hence a graph can easily represents this information. Constrains, are explicit conditions for document clustering where background knowledge is use to set the direction for Linking or Not-Linking a set of documents for a target clusters, thus guiding the clustering process. We deemed clustering is an ill-define problem, there can be many clustering results. Background knowledge can be used to drive the clustering algorithm in the right direction. We have proposed three different types of constraints, Instance level, corpus level and cluster level constraints. A new algorithm Constrained HAC is also proposed which will incorporate Instance level constraints as prior knowledge; it will guide the clustering process leading to better results. Extensive set of experiments have been performed on both synthetic and standard document clustering datasets, results are compared on standard clustering measures like: purity, entropy and F-measure. Results clearly establish that our proposed approach leads to improvement in cluster quality.

cs.IR↗

arXiv2013

An improved semantic similarity measure for document clustering based on topic maps

A major computational burden, while performing document clustering, is the calculation of similarity measure between a pair of documents. Similarity measure is a function that assigns a real number between 0 and 1 to a pair of documents, depending upon the degree of similarity between them. A value of zero means that the documents are completely dissimilar whereas a value of one indicates that the documents are practically identical. Traditionally, vector-based models have been used for computing the document similarity. The vector-based models represent several features present in documents. These approaches to similarity measures, in general, cannot account for the semantics of the document. Documents written in human languages contain contexts and the words used to describe these contexts are generally semantically related. Motivated by this fact, many researchers have proposed seman-tic-based similarity measures by utilizing text annotation through external thesauruses like WordNet (a lexical database). In this paper, we define a semantic similarity measure based on documents represented in topic maps. Topic maps are rapidly becoming an industrial standard for knowledge representation with a focus for later search and extraction. The documents are transformed into a topic map based coded knowledge and the similarity between a pair of documents is represented as a correlation between the common patterns (sub-trees). The experimental studies on the text mining datasets reveal that this new similarity measure is more effective as compared to commonly used similarity measures in text clustering.

cs.IR↗

arXiv2013

A comparison of SVM and RVM for Document Classification

Document classification is a task of assigning a new unclassified document to one of the predefined set of classes. The content based document classification uses the content of the document with some weighting criteria to assign it to one of the predefined classes. It is a major task in library science, electronic document management systems and information sciences. This paper investigates document classification by using two different classification techniques (1) Support Vector Machine (SVM) and (2) Relevance Vector Machine (RVM). SVM is a supervised machine learning technique that can be used for classification task. In its basic form, SVM represents the instances of the data into space and tries to separate the distinct classes by a maximum possible wide gap (hyper plane) that separates the classes. On the other hand RVM uses probabilistic measure to define this separation space. RVM uses Bayesian inference to obtain succinct solution, thus RVM uses significantly fewer basis functions. Experimental studies on three standard text classification datasets reveal that although RVM takes more training time, its classification is much better as compared to SVM.

cs.IR↗

arXiv2012

Content-based Text Categorization using Wikitology

A major computational burden, while performing document clustering, is the calculation of similarity measure between a pair of documents. Similarity measure is a function that assign a real number between 0 and 1 to a pair of documents, depending upon the degree of similarity between them. A value of zero means that the documents are completely dissimilar whereas a value of one indicates that the documents are practically identical. Traditionally, vector-based models have been used for computing the document similarity. The vector-based models represent several features present in documents. These approaches to similarity measures, in general, cannot account for the semantics of the document. Documents written in human languages contain contexts and the words used to describe these contexts are generally semantically related. Motivated by this fact, many researchers have proposed semantic-based similarity measures by utilizing text annotation through external thesauruses like WordNet (a lexical database). In this paper, we define a semantic similarity measure based on documents represented in topic maps. Topic maps are rapidly becoming an industrial standard for knowledge representation with a focus for later search and extraction. The documents are transformed into a topic map based coded knowledge and the similarity between a pair of documents is represented as a correlation between the common patterns. The experimental studies on the text mining datasets reveal that this new similarity measure is more effective as compared to commonly used similarity measures in text clustering.

cs.IR↗