Erkin Çilden

发表

A History Tree Heuristic to Generate Better Initiation Sets for Options in Reinforcement Learning

Faruk Polat, Alper Demir, Erkin Çilden, 2016, ECAI.

Generating Effective Initiation Sets for Subgoal-Driven options

Faruk Polat, Alper Demir, Erkin Çilden, 2019, Adv. Complex Syst..

Abstraction in Model Based Partially Observable Reinforcement Learning Using Extended Sequence Trees

Faruk Polat, Erkin Çilden, Faruk Polat, 2012, 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

Memory efficient factored abstraction for reinforcement learning

Faruk Polat, Erkin Çilden, Coskun Sahin, 2015, 2015 IEEE 2nd International Conference on Cybernetics (CYBCONF).

Landmark Based Reward Shaping in Reinforcement Learning with Hidden States

Faruk Polat, Alper Demir, Erkin Çilden, 2019, AAMAS.

Compact Frequency Memory for Reinforcement Learning with Hidden States

Faruk Polat, Erkin Çilden, Hüseyin Aydin, 2019, PRIMA.

A Generic Distributed Architecture to Integrate Simulated Participants with Modular Avionics

Erkin Çilden, Emre Gultekin, Dogan Poyraz, 2018, 2018 IEEE/ACM 22nd International Symposium on Distributed Simulation and Real Time Applications (DS-RT).

A reference architecture for military simulations with experimentation and analysis features

Erkin Çilden, Ahmet Sezer, M. Haluk Canberi, 2019, SummerSim.

Automatic landmark discovery for learning agents under partial observability

Faruk Polat, Alper Demir, Erkin Çilden, 2019, The Knowledge Engineering Review.

Toward Generalization of Automated Temporal Abstraction to Partially Observable Reinforcement Learning

Faruk Polat, Erkin Çilden, Faruk Polat, 2015, IEEE Transactions on Cybernetics.

Local Roots: A Tree-Based Subgoal Discovery Method to Accelerate Reinforcement Learning

Faruk Polat, Alper Demir, Erkin Çilden, 2016, ECML/PKDD.

Network packet loss sensitivity analysis for sympes codec

Erkin Çilden, Emre Gultekin, M. Haluk Canberi, 2018, 2018 26th Signal Processing and Communications Applications Conference (SIU).

A Concept Filtering Approach for Diverse Density to Discover Subgoals in Reinforcement Learning

Faruk Polat, Alper Demir, Erkin Çilden, 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

Generating Memoryless Policies Faster Using Automatic Temporal Abstractions for Reinforcement Learning with Hidden State

Faruk Polat, Erkin Çilden, Faruk Polat, 2013, 2013 IEEE 25th International Conference on Tools with Artificial Intelligence.

Employing Automatic Temporal Abstractions to Accelerate Utile Suffix Memory Algorithm

Faruk Polat, Erkin Çilden, Faruk Polat, 2014, MATES.

Using Transitional Bottlenecks to Improve Learning in Nearest Sequence Memory Algorithm

Faruk Polat, Erkin Çilden, Hüseyin Aydin, 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

A configurable gateway for DDS-HLA interoperability

Erkin Çilden, Muhammed Cagri Kaya, Alper Karamanlioglu, 2019, SummerSim.