osu!mania Reinforcement Learning Agent - PowerPoint PPT Presentation

Feb 13, 2023 •6 likes •136 views

osu!mania Reinforcement Learning Agent ichrysomallis@isc.tuc.gr 2014030078 Contents Introduction osu!mania game Graphical User Interface customization Agents environment Approach and

osu!mania Reinforcement Learning Agent Χρυσομάλλης Ιάσων ichrysomallis@isc.tuc.gr 2014030078
Contents  Introduction  osu!mania game  Graphical User Interface customization  Agent’s environment  Approach and variable definition  Q-learning  Deep reinforcement learning  Future plans 2
Introduction Topic: Develop an agent able to learn how to play the video game osu!mania, through reinforcement learning. Two agents :  Q-learning agent  Deep reinforcement learning agent 3
osu!mania game Rhythm game , notes are falling Single-tap notes 1. Hold notes 2. Judgment bar 3. Player keys 4. Combo 5. Hitburst 6. Overall accuracy 7. Score 8. 4
Graphical User Interface customization Fully customizable environment, all elements can be changed Each element is painted with solid color RGB = [X, 100, 100], where X is in accordance with the element’s identity (see numbers) 5
Agent’s environment Record screenshots and translate information based on the RGB values given Small fraction of the screen includes relevant information , specific boxes are being recorded 6
Approach and variable definition (1) Identical behavior on each column, problem can be narrowed down to single column learning  Agent’s actions : Instantaneous key tap 1. Key press (no release) 2. Key release 3. Do nothing 4. 7
Approach and variable definition ( 2 )  Rewards:  Epsilon: o Initial value = 1 o Decay value = 0.9977 o Minimum value = 0.01 8
Approach and variable definition ( 3 )  State:  One column of 200 pixels  Only red (R) layer  Three possible values (no note, singe-tap note, hold note) Deep reinforcement learning: o Raw input of the column Q-learning: o Only 8 pixels due to state complexity, taking one pixel every 15 pixels of the recorded column 9
Q-learning  Algorithm:  Steps:  Receive current state  Choose an action based on epsilon  Execute the action  Receive new state  Check if song is over  Update Q-table 10
Deep reinforcement learning  Neural network model (Keras):  Steps: Identical steps apart from last one. Save transitions in temporary memory and train the model with a smaller, randomly selected sample group (batch). 11
Results Q-learning agent DQN agent 12
Future plans  Try different combinations of neural network model layers  Design the neural network model in TensorFlow  Run the agent on GPU, instead of CPU  Make use of a high end computer 13

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Multi-agent learning Multi-agent reinforcement learning Gerard Vreeswijk , Intelligent Systems

Multi-agent learning Multi-agent reinforcement learning Multi-agent learning Multi-agent reinforcement learning Gerard Vreeswijk , Intelligent Systems Group, Computer Science Department, Faculty of Sciences, Utrecht University, The Netherlands.

752 views • 21 slides

Foundations of Machine Learning Reinforcement Learning Reinforcement Learning Agent exploring

Foundations of Machine Learning Reinforcement Learning Reinforcement Learning Agent exploring environment. Interactions with environment: action state Agent Environment reward Problem: find action policy that maximizes cumulative reward

828 views • 66 slides

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

Introduction to Reinforcement Learning RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem Inside an RL agent Temporal difference learning Many faces of Reinforcement Learning What is

551 views • 35 slides

REINFORCEMENT LEARNING IN MULTI-AGENT SYSTEMS MACHINE LEARNING MEETUP DR. ANA PELETEIRO

REINFORCEMENT LEARNING IN MULTI-AGENT SYSTEMS MACHINE LEARNING MEETUP DR. ANA PELETEIRO RAMALLO 29-08-2016 TABLE OF CONTENTS MULTI-AGENT SYSTEMS GAME THEORY REINFORCEMENT LEARNING MULTI-AGENT LEARNING 2 ZALANDO Our purpose: to Zalando

1.45k views • 20 slides

Imitation Learning Spring 2019, CMU 10-403 Katerina Fragkiadaki Reinforcement learning Agent

Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Imitation Learning Spring 2019, CMU 10-403 Katerina Fragkiadaki Reinforcement learning Agent state reward action S t R t A t R t+ 1 Environment S t+ 1

1.07k views • 52 slides

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning Kyunghwan Son , Daewoo Kim, Wan Ju Kang, David Hostallero, Yung Yi School of Electrical Engineering, KAIST Cooperative Multi-Agent Reinforcement

662 views • 8 slides

The Reinforcement Learning Problem Robert Platt Northeastern University Agent Action Agent

The Reinforcement Learning Problem Robert Platt Northeastern University Agent Action Agent World Observation Reward On a single time step, agent does the following: 1. observe some information 2. select an action to execute 3. take note

374 views • 11 slides

Reinforcement Learning You can think of supervised learning as the teacher providing answers

Reinforcement Learning You can think of supervised learning as the teacher providing answers (the class labels) Reinforcement learning: In reinforcement learning, the agent learns Markov Decision Processes based on a punishment/reward

89 views • 6 slides

1 The DFG Algorithm - The DFG Algorithm - Rationale The basic cycle Obviously, for each

4.3. Reinforcement learning for forming coalitions: the DFG algorithm Reinforcement Learning (I) Wei (1995) Watkins (1989) DFG: Dissolution and Formation of Groups Lets use our single agent definition: Then an agent Ag has in Dat for each

58 views • 3 slides

Model Based Reinforcement Learning Katerina Fragkiadaki Model Anything the agent can use to

Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Model Based Reinforcement Learning Katerina Fragkiadaki Model Anything the agent can use to predict how the environment will respond to its actions,

826 views • 65 slides

Reinforcement Learning Robert Platt Northeastern University Some images and slides are used

Reinforcement Learning Robert Platt Northeastern University Some images and slides are used from: 1. CS188 UC Berkeley 2. RN, AIMA Conception of agent act Agent World sense RL conception of agent Agent takes actions a Agent World s,r

1.03k views • 39 slides

Reinforcement Learning, cont. Models an agent trying to learn what to do / how to act

Reinforcement Learning, cont. Models an agent trying to learn what to do / how to act in a complex environment. So far, we have seen passive learning We learned utility values for a fixed world with fixed transitions (no real

737 views • 29 slides

Reinforcement Learning Environments Fully-observable vs partially-observable Single agent

Reinforcement Learning Environments Fully-observable vs partially-observable Single agent vs multiple agents Deterministic vs stochastic Episodic vs sequential Static or dynamic Discrete or continuous What is reinforcement

684 views • 39 slides

Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2019 Reinforcement Learning

Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2019 Reinforcement Learning t r t R = max : S A t =0 MDPs Agent interacts with an environment At each time t: Receives sensor signal s t

717 views • 40 slides

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement

1 Deep Reinforcement Learning Qianqian Li, Nayeon Koong, Langtian He What is deep reinforcement learning? Agent/Actor + Action + Environment + State + Reward How does reinforcement learning work?

792 views • 31 slides

Reinforcement Learning Course 9.54 Final review Agent learning to act in an unknown environment

Reinforcement Learning Course 9.54 Final review Agent learning to act in an unknown environment Reinforcement Learning Setup S t Background and setup The environment is initially unknown or partially known It is also stochastic, the

549 views • 31 slides

The New York State Health Workforce Planning Data Guide Presented by: Robert Martiniano, DrPH,

The New York State Health Workforce Planning Data Guide Presented by: Robert Martiniano, DrPH, MPA Senior Program Manager Center for Health Workforce Studies School of Public Health | University at Albany, SUNY rmartiniano@albany.edu Rong

786 views • 14 slides

PAWIKAN: A Scalable Network Management System for the Philippine Research, Education, and

PAWIKAN: A Scalable Network Management System for the Philippine Research, Education, and Government Information Network (PREGINET) http://pawikan.sourceforge.net Authors: Edwin Vinas, Jerremeo Gabas, Paul Afroilan and Rey Babilonia

498 views • 28 slides

pTec Predictive Maintenance Solution Predictive Maintenance Solutions by Indalyz AG What if you

pTec Predictive Maintenance Solution Predictive Maintenance Solutions by Indalyz AG What if you were able to forecastwhen your equipment will fail, or when maintenance should really be performed? Being able to control budgets, downtimes,

1.29k views • 17 slides

Rapid Development of Custom Software Architecture Design Environments Robert T. Monroe Carnegie

Rapid Development of Custom Software Architecture Design Environments Robert T. Monroe Carnegie Mellon University Introduction and Motivation Introduction and motivation Capturing design expertise Customizing design environments

638 views • 62 slides

Water Rights Accounting New Accounting Model New Technology: 1979 versus 2011 Faster

Water Rights Accounting New Accounting Model New Technology: 1979 versus 2011 Faster processors Faster graphics Larger, faster, memory Larger, faster, disk storage Common Application Use single application to build and

585 views • 33 slides

director One system to control them all Director excels at PA system supervision and control

connect. control. monitor. visualize. director One system to control them all Director excels at PA system supervision and control Supported public address systems What is Director and what can it do? Director is a system management so

699 views • 15 slides

I ntroduction of Metros New Website Presented to the Office of the Board Secretary :

I ntroduction of Metros New Website Presented to the Office of the Board Secretary : Riders Advisory Council January 7, 2009 1 Current Enterprise Web Portal Site is rich in content & applications, but disorganized No

541 views • 8 slides

A NEXT -GEN LEARNING MANAGEMENT SYSTEM WHAT IS LMS? A Learning Management System (LMS) is a

A NEXT -GEN LEARNING MANAGEMENT SYSTEM WHAT IS LMS? A Learning Management System (LMS) is a software application or Web based technology used to plan, implement and assess a specific learning process. LMS includes Teacher and Student

493 views • 24 slides