Nasser Mozayani

is this you? claim profile


  • Learning to predict where to look in interactive environments using deep recurrent q-learning

    Bottom-Up (BU) saliency models do not perform well in complex interactive environments where humans are actively engaged in tasks (e.g., sandwich making and playing the video games). In this paper, we leverage Reinforcement Learning (RL) to highlight task-relevant locations of input frames. We propose a soft attention mechanism combined with the Deep Q-Network (DQN) model to teach an RL agent how to play a game and where to look by focusing on the most pertinent parts of its visual input. Our evaluations on several Atari 2600 games show that the soft attention based model could predict fixation locations significantly better than bottom-up models such as Itti-Kochs saliency and Graph-Based Visual Saliency (GBVS) models.

    12/17/2016 ∙ by Sajad Mousavi, et al. ∙ 0 share

    read it

  • A new Potential-Based Reward Shaping for Reinforcement Learning Agent

    Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps in the process of transfer learning: extracting knowledge from previously learned tasks and transferring that knowledge to use it in a target task. The latter step is well discussed in the literature with various methods being proposed for it, while the former has been explored less. With this in mind, the type of knowledge that is transmitted is very important and can lead to considerable improvement. Among the literature of both the transfer learning and the potential-based reward shaping, a subject that has never been addressed is the knowledge gathered during the learning process itself. In this paper, we presented a novel potential-based reward shaping method that attempted to extract knowledge from the learning process. The proposed method extracts knowledge from episodes' cumulative rewards. The proposed method has been evaluated in the Arcade learning environment and the results indicate an improvement in the learning process in both the single-task and the multi-task reinforcement learner agents.

    02/17/2019 ∙ by Babak Badnava, et al. ∙ 0 share

    read it