• case-insensitive prefix search: default
  e.g., sig matches "SIGIR" as well as "signal"
• exact word search: append dollar sign ($) to word
  e.g., graph$ matches "graph", but not "graphics"
• boolean and: separate words by space
  e.g., codd model
• boolean or: connect words by pipe symbol (|)
  e.g., graph|network

Update May 7, 2017: Please note that we had to disable the phrase search operator (.) and the boolean not operator (-) due to technical problems. For the time being, phrase search queries will yield regular prefix search result, and search terms preceded by a minus will be interpreted as regular (positive) search terms.

found 22 matches

• 2024
• 
  Saim Sunel, Erkin Çilden, Faruk Polat:
  Faster MIL-based Subgoal Identification for Reinforcement Learning by Tuning Fewer Hyperparameters. ACM Trans. Auton. Adapt. Syst. 19(2): 10 (2024)
• 2023
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Landmark based guidance for reinforcement learning agents under partial observability. Int. J. Mach. Learn. Cybern. 14(4): 1543-1563 (2023)
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Correction: Landmark based guidance for reinforcement learning agents under partial observability. Int. J. Mach. Learn. Cybern. 14(4): 1565 (2023)
• 2022
• 
  Hüseyin Aydin, Erkin Çilden, Faruk Polat:
  Using chains of bottleneck transitions to decompose and solve reinforcement learning tasks with hidden states. Future Gener. Comput. Syst. 133: 153-168 (2022)
• 2019
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Generating Effective Initiation Sets for Subgoal-Driven options. Adv. Complex Syst. 22(2): 1950001:1-1950001:32 (2019)
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Automatic landmark discovery for learning agents under partial observability. Knowl. Eng. Rev. 34: e11 (2019)
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Landmark Based Reward Shaping in Reinforcement Learning with Hidden States. AAMAS 2019: 1922-1924
• 
  Hüseyin Aydin, Erkin Çilden, Faruk Polat:
  Compact Frequency Memory for Reinforcement Learning with Hidden States. PRIMA 2019: 425-433
• 
  Muhammed Cagri Kaya, Alper Karamanlioglu, I. Çaglar Çetintas, Erkin Çilden, M. Haluk Canberi, Halit Oguztüzün:
  A configurable gateway for DDS-HLA interoperability. SummerSim 2019: 36:1-36:11
• 
  Gökçe Özkan, Erkin Çilden, Emre Gültekin, Ahmet Sezer, M. Haluk Canberi:
  A reference architecture for military simulations with experimentation and analysis features. SummerSim 2019: 64:1-64:6
• 2018
• 
  Erkin Çilden, Emre Gultekin, Dogan Poyraz, M. Haluk Canberi:
  A Generic Distributed Architecture to Integrate Simulated Participants with Modular Avionics. DS-RT 2018: 222-223
• 
  Erhan Ceran, Erkin Çilden, Emre Gultekin, M. Haluk Canberi:
  Network packet loss sensitivity analysis for sympes codec. SIU 2018: 1-4
• 2017
• 
  Hüseyin Aydin, Erkin Çilden, Faruk Polat:
  Using Transitional Bottlenecks to Improve Learning in Nearest Sequence Memory Algorithm. ICTAI 2017: 147-152
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  A Concept Filtering Approach for Diverse Density to Discover Subgoals in Reinforcement Learning. ICTAI 2017: 1-5
• 2016
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  A History Tree Heuristic to Generate Better Initiation Sets for Options in Reinforcement Learning. ECAI 2016: 1644-1645
• 
  Alper Demir, Erkin Çilden, Faruk Polat:
  Local Roots: A Tree-Based Subgoal Discovery Method to Accelerate Reinforcement Learning. ECML/PKDD (2) 2016: 361-376
• 2015
• 
  Erkin Çilden, Faruk Polat:
  Toward Generalization of Automated Temporal Abstraction to Partially Observable Reinforcement Learning. IEEE Trans. Cybern. 45(8): 1414-1425 (2015)
• 
  Coskun Sahin, Erkin Çilden, Faruk Polat:
  Memory efficient factored abstraction for reinforcement learning. CYBCONF 2015: 18-23
• 2014
• 
  Erkin Çilden:
  Abstraction in reinforcement learning in partially observable environments ; Kısmi gözlemlenebilir ortamlar için pekiştirmeli öğrenmede soyutlama. Middle East Technical University, Çankaya, Ankara, Turkey, 2014
• 
  Erkin Çilden, Faruk Polat:
  Employing Automatic Temporal Abstractions to Accelerate Utile Suffix Memory Algorithm. MATES 2014: 156-169
• 2013
• 
  Erkin Çilden, Faruk Polat:
  Generating Memoryless Policies Faster Using Automatic Temporal Abstractions for Reinforcement Learning with Hidden State. ICTAI 2013: 719-726
• 2012
• 
  Erkin Çilden, Faruk Polat:
  Abstraction in Model Based Partially Observable Reinforcement Learning Using Extended Sequence Trees. IAT 2012: 348-355