reinforcement learning of reinforcement learning of
play

Reinforcement Learning of Reinforcement Learning of Affordance Cues - PowerPoint PPT Presentation

Sep 15, 2022 •467 likes •640 views

Reinforcement Learning of Reinforcement Learning of Affordance Cues Affordance Cues Final Status of Work Final Status of Work Lucas Paletta & Gerald Fritz Lucas Paletta & Gerald Fritz Computational Perception Group Computational

  1. Reinforcement Learning of Reinforcement Learning of Affordance Cues Affordance Cues Final Status of Work Final Status of Work Lucas Paletta & Gerald Fritz Lucas Paletta & Gerald Fritz Computational Perception Group Computational Perception Group Institute of Digital Image Processing Institute of Digital Image Processing JOANNEUM RESEARCH Forschungsgesellschaft Forschungsgesellschaft mbH mbH JOANNEUM RESEARCH Graz, Austria Graz, Austria Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  2. Perception Module Perception Module Architecture Architecture Learning Learning of of affordance affordance cues cues Feature detectors detectors Feature Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  3. Perception and Learning Perception and Learning Supervised Learning of Supervised Learning of Affordance Cues Affordance Cues top = T Y circular = T unknown N size > 1426 liftable non liftable Y N size < 1410 liftable Y pruning pruning liftable non liftable Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  4. Perception and Learning Perception and Learning Affordance Hypotheses Affordance Hypotheses tb = bottom: unknown (1086.0) tb = top: | structure = circ: non liftable (552.0) P(A liftable |circ) ≈ 0.00 | structure = rect: | | size > 1426 : liftable (402.0) P(A nonliftable |circ) ≈ 1.00 | | size <= 1426 : P(A liftable |rect) ≈ 0.99 | | | size <= 1410 : liftable (72.0) P(A nonliftable |rect) ≈ 0.01 | | | size > 1410 : non liftable (6.0) Fritz et al., SAB 2006, IROS 2006 Fritz et al., SAB 2006, IROS 2006 Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  5. Integration of Integration of Perception Module and Module and Perception Learning Module Module Learning Outcome Classifier Classifier Outcome LM LM outcome outcome ‚Interaction ‚ Interaction‘ ‘ DT Estimator DT Estimator Affordance Cue Cue Classifier Classifier Affordance EM EM BM BM Entity Entity Memory Memory PM SUPERVISED SUPERVISED PM Feature Detectors Feature Detectors (DECISION TREE ) (DECISION TREE ) LEARNING LEARNING Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  6. Decision Processes, Decision Processes, Rewards & Affordance Cues Rewards & Affordance Cues reward perceptual perceptual state state (spatiotemp ( spatiotemp) ) trigger cue state cue actions actions affordance outcome outcome recognition Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  7. Closed-Loop Learning Closed-Loop Learning ATTENTION ATTENTION FEATURE RECOGNITION FEATURE RECOGNITION LEARNING & CONTROL LEARNING & CONTROL Entities, State Image s t Curiosity Drive s Attributes Estimation Analysis t Final State Recognition R t R t MDP Decision Maker a t a t Paletta & Fritz, ICDL 2007 Paletta & Fritz, ICDL 2007 Paletta & Fritz, KI 2007 Paletta & Fritz, KI 2007 Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  8. Reinforcement (Q-)Learning Reinforcement (Q-)Learning gripper gripper gripper gripper down down down down  States : multi-modal & proprioceptive features  States final state  Actions : motor , crane, camera (a 1 ,.., a A )  Actions gripper gripper gripper gripper up up Object Object up up Object   Rewards : reward function is specific to Rewards HIGH & LOW & s MID & s‘ s‘‘ affordance outcome driven reward : Gripper Gripper Gripper HIGH LOW MID  R(t+1) = 1 if outcome occurs R = 0 R = +1  R(t+1) = 0 otherwise predicted reward of Predicted Reward Update Rule early trigger state � � � � � � � n � � Q ( s , a ) U ( S , a ) E R ( s , a ) ( ) � Q ( s , a ) 1 Q ( s , a ) R max Q ( s ' , a ' ) � � � = � � � � + � + � � � t n t n t n + + + � � a ' � � � � n 0 = � � � � Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  9. Generalized Trigger Features and Generalized Trigger Features and Execution of Interaction Execution of Interaction agent agent full state description affordance classifier 1 affordance classifier 2 affordance classifier 3 affordance classifier4  classification tree b1 b2 b3 b4 (generalization on predictive perceptual state s t reward R t action a t features) environment Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  10. Integration of Integration of Perception Module and Module and Perception Learning Module Module Learning EM EM Outcome Outcome Classifier Classifier ‚Interaction Interaction‘ ‘ ‚ Affordance Cue Cue Classifier Classifier Affordance outcome outcome (actual reward) (actual reward) reward estimate reward estimate BM BM Parameter Estimator Estimator Parameter Reward Estimator Estimator Reward parameters parameters LM LM EXPLORATORY EXPLORATORY Feature Detectors Detectors Feature (REINFORCEMENT ) (REINFORCEMENT ) LEARNING LEARNING PM PM Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  11. Predicted Reward & Predicted Reward & Perceptual States Perceptual States est est. . future future cumulative cumulative reward reward ← ← classification classification affordance affordance cue cue ← ← Demonstration ← proprioceptive proprioceptive features features ← observation observation of of own own actions actions ← ← ← observation observation of of environment environment ← Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  12. Perception and Learning Perception and Learning Reinforcement Learning of Reinforcement Learning of Affordance based Cues Affordance based Cues prospective states and affordance cues Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  13. Perception and Learning Perception and Learning Learning on Real World Imagery on Real World Imagery Learning  Real World Images with Image Analysis  Simulation of Magnet signals and Crane´s Rope Tension Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  14. Perception and Learning Perception and Learning Video on Real-World Data Video on Real-World Data Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  15. Perception and Learning Perception and Learning Key Contributions Key Contributions  Reinforcement Learning Methodology for Affordance Cueing ⇒ Exploratory Learning without Supervision Exploratory Learning without Supervision ⇒ Reward Signal Determines Outcome Events ⇒ Reward Signal Determines Outcome Events ⇒ Backtracking Determines Perceptual ‘ ‘Cue Cue’ ’ State State ⇒ Backtracking Determines Perceptual ⇒ ⇒ Enables Largely Autonomous Learning of Cueing Enables Largely Autonomous Learning of Cueing ⇒  Perception-Action Framework for Affordance Recognition ⇒ Implicit Learning of Affordance Relations Implicit Learning of Affordance Relations Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

  16. Perception and Learning Perception and Learning Directions of Future Work Directions of Future Work  Generalisation Towards Higher Order Features  Unsupervised Segmentation of Affordance Processing Stages (C, B, O)  Integration into an Affordance Selection Framework Lucas PALETTA - Computational Perception Group (CAPE) MACS YEAR 3 REVIEW MEETING, Sankt Augustin, February 15, 2008

Recommend

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

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 Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine playing a new game whose rules you dont know; after a hundred or so moves your don t know; after a hundred or so moves, your opponent announces, You

511 views • 30 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

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
Examples of Reinforcement Learning Robocup Soccer Teams Stone &amp; Veloso, Reidmiller et al.

Examples of Reinforcement Learning Robocup Soccer Teams Stone &amp; Veloso, Reidmiller et al.

Reinforcement Learning Slides by Rich Sutton Mods by Dan Lizotte Refer to Reinforcement Learning: An Introduction by Sutton and Barto Alpaydin Chapter 16 Up until now we have been Supervised Learning Classifying, mostly

891 views • 31 slides
CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning Haarnoja, Tang et al. (2017) Reinforcement Learning with Deep Energy Based Policies, ICML . Haarnoja, Zhou et al. (2018) Soft Actor-Critic: Off-Policy

683 views • 24 slides
Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control Theory, you actually have some knowledge in RL. RL shares the overall goal with OCT: solving for a control policy such that the cumulative cost

610 views • 22 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still assume a Marko kov decision process (MDP): A se set o of st states s s S A se set o of a actions ( s (per st state) A A mo model

96 views • 5 slides
R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec 03 2008 1 Large State Spaces h When a problem has a large state space we can not longer represent the U or Q functions as explicit tables explicit

436 views • 18 slides
Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning&lt;br/&gt;&lt;br/&gt; 4/25/19, 8*06 PM Reinforcement Learning&lt;br/&gt;&lt;br/&gt; 4/25/19, 8*06 PM Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning? Spring 2019 Created:

371 views • 15 slides
7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B. Temporal Difference Reinforcement Learning C. PVLV Model D. Cerebellum and Error-driven Learning 2/23/18 COSC 494/594 CCN 2 Sensory-Motor Loop

790 views • 56 slides
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

541 views • 15 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi Willem van de Meent Northeastern University [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188

145 views • 10 slides
Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning: an Introduction, 2nd Edition: Chapters 6 (6.1 6.5) Outline Reinforcement Learning Reinforcement Learning: the

587 views • 27 slides
Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and Reinforcement Learning University of Waterloo Machine Learning Supervised Learning Teacher tells learner what to remember Reinforcement Learning

401 views • 29 slides
1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

CSE 573: Artificial Intelligence Todo Reinforcement Learning Add simulations from 473 Dan Weld Add UCB bound (cut bolzman &amp; constant epsilon Add snazzy videos (pendulum, zico kolter See http://www See http://www-

462 views • 11 slides
Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest Lecture May 24, 2017 Lecture overview What makes a reinforcement learning algorithm safe ? Notation Creating a safe reinforcement learning

1.42k views • 88 slides
Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

1 Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5 Environment Dynamics Gillian Hayes Components of a Problem 18th January 2007 Values and Action Values, V and Q Optimal Policies

109 views • 7 slides
Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007 sequential decision making under uncertainty ? How Can I ... ? Move around in the physical world (e.g. driving, navigation) Play and win a game

519 views • 21 slides
Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper

Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper

Neural Combinatorial Optimization With Reinforcement Learning CS885 Reinforcement Learning Paper by Bello, I., Pham, H., Le, Q. V., Norouzi, M., &amp; Bengio, S. (2016) Presented by Yan Shi Outline 1. Introduction 2. Background 3. Algorithms

966 views • 27 slides
Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value

Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value

5/7/2012 CSE 473: Artificial Intelligence Todays Outline Reinforcement Learning Dan Weld Reinforcement Learning Q-value iteration Q-learning Exploration / exploitation Linear function approximation Linear function

159 views • 12 slides
CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement

CSC2621 Topics in Robotics Reinforcement Learning in Robotics Week 11: Hierarchical Reinforcement Learning Animesh Garg Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning Richard S. Sutton , Doina

2.18k views • 29 slides
Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M.

Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M.

Reinforcement Learning (RL) CE-717: Machine Learning Sharif University of Technology M. Soleymani Fall 2018 Most slides have been taken from Klein and Abdeel, CS188, UC Berkeley. Reinforcement Learning (RL) Learning as a result of

1.45k views • 133 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

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
Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain

Machine Learning for NLP Reinforcement learning Aurlie Herbelot 2019 Centre for Mind/Brain Sciences University of Trento 1 Introduction 2 Reinforcement learning: intuition Reinforcement learning: like learning to ride a bicycle.

1.18k views • 58 slides

More recommend