M. M. Hassan Mahmud

Learn More
In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have been used successfully in practice and PAC analysis of these methods have been developed. But the key notion of relatedness between tasks has not yet been defined clearly, which(More)
Different interfaces allow a user to achieve the same end goal through different action sequences, e.g., command lines vs. drop down menus. Interface efficiency can be described in terms of a cost incurred, e.g., time taken, by the user in typical tasks. Realistic users arrive at evaluations of efficiency, hence making choices about which interface to use,(More)
POMDPs are the models of choice for reinforcement learning (RL) tasks where the environment cannot be observed directly. In many applications we need to learn the POMDP structure and parameters from experience and this is considered to be a difficult problem. In this paper we address this issue by modeling the hidden environment with a novel class of models(More)
Interactive interfaces are a common feature of many systems ranging from field robotics to video games. In most applications , these interfaces must be used by a heterogeneous set of users, with substantial variety in effectiveness with the same interface when configured differently. We address the issue of personalizing such an interface, adapting(More)
In this paper we introduce the MDP-with-agents model for addressing a particular sub-class of non-stationary environments where the learner is required to interact with other agents. The behavior-policies of the agents are determined by a latent variable that changes rarely, but can modify the agent policies drastically when it does change (like traffic(More)
We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement learning. This is necessary when the number of previous tasks is large and the cost of measuring similarity counteracts the(More)
In this paper we discuss the notion of functional similarity between different situations an artificial agent may encounter, and show how it may be used to transfer information across tasks. We say two situations are functionally similar (FS) if there exists an action that has a similar effect in both the situations. So for instance, many situations(More)
We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement learning. This is necessary when the number of previous tasks is large and the cost of measuring similarity counteracts the(More)
The effective use of an E-Government (EG) Portal depends on the ability of people to utilize electronic services. One of the main challenges in developing the EG Portal is selecting usability design guidelines that addressed the overall EG functions. Most government agencies tend to design their portal based on existing guidelines that are not directly(More)
Interactive interfaces are a common feature of many systems ranging from field robotics to video games. In most applications, these interfaces must be used by a heterogeneous set of users, with substantial variety in effectiveness with the same interface when configured differently. We address the problem of personalizing such an interface, adapting(More)
  • 1