Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning

Date

2020-04-01

Author

Aydın, Ayberk
Sürer, Elif

Metadata

Show full item record

Item Usage Stats

299
views

0
downloads

Deep Reinforcement Learning (DRL) has been suc-cessfully applied in several research domains such as robotnavigation and automated video game playing. However, thesemethods require excessive computation and interaction with theenvironment, so enhancements on sample efficiency are required.The main reason for this requirement is that sparse and delayedrewards do not provide an effective supervision for representationlearning of deep neural networks. In this study, Proximal PolicyOptimization (PPO) algorithm is augmented with GenerativeAdversarial Networks (GANs) to increase the sample efficiency byenforcing the network to learn efficient representations withoutdepending on sparse and delayed rewards as supervision. Theresults show that an increased performance can be obtained byjointly training a DRL agent with a GAN discriminator.

Subject Keywords

Deep learning, Reinforcement learning, Genera-tive adversarial networks

URI

https://arxiv.org/abs/2004.02762
https://hdl.handle.net/11511/79368

Collections

Unverified, Article

Suggestions

OpenMETU
Core

Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning Aydın, Ayberk; Sürer, Elif (2020-10-05) Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the environment, so enhancements on sample efficiency are required. The main reason for this requirement is that sparse and delayed rewards do not provide an effective supervision for representation learning of deep neural networks. In this study, Proximal Policy Optimization (PPO) algo...
AUTOMATED VIDEO GAME TESTING USING REINFORCEMENT LEARNING AGENTS Arıyürek, Sinan; Sürer, Elif; Betin Can, Aysu; Department of Bioinformatics (2022-9-21) In this thesis, several methodologies are introduced to automate and improve video game playtesting. These methods are based on Reinforcement Learning (RL) agents. First, synthetic and human-like tester agents are proposed to automate video game testing. The synthetic agent uses test goals generated from game scenarios, and the human-like agent uses test goals extracted from tester trajectories. Tester agents are derived from Sarsa and Monte Carlo Tree Search (MCTS) but focus on finding defects, while tradi...
Deep Learning-Based Hybrid Approach for Phase Retrieval IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24) We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
Learning to play an imperfect information card game using reinforcement learning Alpaslan, Ferda Nur; Baykal, Ömer; Demirdöver, Buğra Kaan (2022-08-01) Artificial intelligence and machine learning are widely popular in many areas. One of the most popular ones is gaming. Games are perfect testbeds for machine learning and artificial intelligence with various scenarios and types. This study aims to develop a self-learning intelligent agent to play the Hearts game. Hearts is one of the most popular trick-taking card games around the world. It is an imperfect information card game. In addition to having a huge state space, Hearts offers many extra challenges d...
Using Multi-Agent Reinforcement Learning in Auction Simulations Kanmaz, Medet; Sürer, Elif (2020-04-01) Game theory has been developed by scientists as a theory of strategic interaction among players who are supposed to be perfectly rational. These strategic interactions might have been presented in an auction, a business negotiation, a chess game, or even in a political conflict aroused between different agents. In this study, the strategic (rational) agents created by reinforcement learning algorithms are supposed to be bidder agents in various types of auction mechanisms such as British Auction, Sealed Bid...

Citation Formats

A. Aydın and E. Sürer, “Using Generative Adversarial Nets on Atari Games for Feature Extraction in Deep Reinforcement Learning,” 2020, Accessed: 00, 2021. [Online]. Available: https://arxiv.org/abs/2004.02762.