EMDD-RL: faster subgoal identification with diverse density in reinforcement learning

Download
2021-1-15
Sunel, Saim
Diverse Density (DD) algorithm is a well-known multiple instance learning method, also known to be effective to automatically identify sub-goals and improve Reinforcement Learning (RL). Expectation-Maximization Diverse Density (EMDD) improves DD in terms of both speed and accuracy. This study adapts EMDD to automatically identify subgoals for RL which is shown to perform significantly faster (3 to 10 times) than its predecessor, without sacrificing solution quality. The performance of the proposed method named EMDD-RL is empirically shown via extensive experimentation, together with the discussions on the effects of EMDD hyperparameters on the results.

Suggestions

A Concept Filtering Approach for Diverse Density to Discover Subgoals in Reinforcement Learning
DEMİR, ALPER; Cilden, Erkin; Polat, Faruk (2017-11-08)
In the reinforcement learning context, subgoal discovery methods aim to find bottlenecks in problem state space so that the problem can naturally be decomposed into smaller subproblems. In this paper, we propose a concept filtering method that extends an existing subgoal discovery method, namely diverse density, to be used for both fully and partially observable RL problems. The proposed method is successful in discovering useful subgoals with the help of multiple instance learning. Compared to the original...
Improving reinforcement learning using distinctive clues of the environment
Demir, Alper; Polat, Faruk; Department of Computer Engineering (2019)
Effective decomposition and abstraction has been shown to improve the performance of Reinforcement Learning. An agent can use the clues from the environment to either partition the problem into sub-problems or get informed about its progress in a given task. In a fully observable environment such clues may come from subgoals while in a partially observable environment they may be provided by unique experiences. The contribution of this thesis is two fold; first improvements over automatic subgoal identifica...
TSP Race: Minimizing completion time in time-sensitive applications
Çavdar, Bahar; Sokol, Joel (2015-07-01)
In this paper, we present an approach for parallelizing computation and implementation time for problems where the objective is to complete the solution as soon after receiving the problem instance as possible. We demonstrate the approach on the TSP. We define the TSP race problem, present a computation-implementation parallelized (CIP) approach for solving it, and demonstrate CIP's effectiveness on TSP Race instances. We also demonstrate a method for determining a priori when CIP will be effective. Althoug...
Online collaboration: Collaborative behavior patterns and factors affecting globally distributed team performance
Serce, Fatma Cemile; Swigger, Kathleen; Alpaslan, Ferda Nur; Brazile, Robert; Dafoulas, George; Lopez, Victor (2011-01-01)
Studying the collaborative behavior of online learning teams and how this behavior is related to communication mode and task type is a complex process. Research about small group learning suggests that a higher percentage of social interactions occur in synchronous rather than asynchronous mode, and that students spend more time in task-oriented interaction in asynchronous discussions than in synchronous mode. This study analyzed the collaborative interaction patterns of global software development learning...
GMDH: An R Package for Short Term Forecasting via GMDH-Type Neural Network Algorithms
DAĞ, OSMAN; Yozgatlıgil, Ceylan (2016-08-01)
Group Method of Data Handling (GMDH)-type neural network algorithms are the heuristic self organization method for the modelling of complex systems. GMDH algorithms are utilized for a variety of purposes, examples include identification of physical laws, the extrapolation of physical fields, pattern recognition, clustering, the approximation of multidimensional processes, forecasting without models, etc. In this study, the R package GMDH is presented to make short term forecasting through GMDH-type neural n...
Citation Formats
S. Sunel, “EMDD-RL: faster subgoal identification with diverse density in reinforcement learning,” M.S. - Master of Science, Middle East Technical University, 2021.