reinforcement learning in humans and animals
play

reinforcement learning in humans and animals nathaniel daw nyu - PowerPoint PPT Presentation

Jan 14, 2023 •174 likes •449 views

reinforcement learning in humans and animals nathaniel daw nyu neuroscience; psychology; neuroeconomics cognition centric roundtable stevens, may 13 2011 collaborators NYU: Aaron Bornstein Sara Constantino Nick Gustafson Jian Li Seth

  1. reinforcement learning in humans and animals nathaniel daw nyu neuroscience; psychology; neuroeconomics cognition centric roundtable stevens, may 13 2011

  2. collaborators NYU: Aaron Bornstein Sara Constantino Nick Gustafson Jian Li Seth Madlon-Kay Dylan Simon Bijan Pesaran Columbia: Daphna Shohamy Elliott Wimmer UCL: Peter Dayan Ben Seymour Ray Dolan Berkeley: Bianca Wittmann U Chicago: Jeff Beeler Xiaoji Zhuang Princeton: Yael Niv Sam Gershman Trinity: John O’Doherty Tel Aviv: Tom Schonberg Daphna Joel Montreal: Aaron Courville CMU: David Touretzky Austin: Ross Otto funding: NIMH, NIDA, NARSAD, McKnight Endowment, HFSP

  3. question longstanding question in psychology: what information is learned from reward – law of effect (Thorndike): learn to repeat reinforced actions • dopamine – cognitive maps (Tolman): learn “map” of task structure; evaluate new actions online • even rats can do this

  4. new leverage on this problem draw on computer science, economics for methods, frameworks 1.new computational & neural tools – examine learning via trial-by-trial adjustments in behavior and neural signals 1.new computational theories – algorithmic view – dopamine associated with “model-free” RL – “model-based” RL as account for cognitive maps (Daw, Niv & Dayan 2005, 2006)

  5. learned decision making in humans 0.5 probability 0.25 + 0 0.5 “bandit” tasks probability Daw et al. 2006 0.25 Wittmann et al 2008 Gershman et al 2009 Schonberg et al 2007, 2010 Glascher et al. 2010 0 Li & Daw 2011 0 100 200 300 trial

  6. trial-by-trial analysis … t-3 t-4 t-1 t-2 experience (past choices & outcomes) Probability model predicted values (RL algorithm + prediction errors probabilistic choice rule: etc experience  choices) Choice behavior: predicted choice which model & parameters make observed choices most likely? (probabilities)

  7. Â Â

  8. Á

  9. ? Á E[ V ( a )] = Σ o P( o | a ) V ( o ) “model- “model- based” free”

  10. rat version (Balleine, Daw & O’Doherty, 2009) Lever Presses Valued (Holland, 2004) Devalued two behavioral modes: 10 devaluation-sensitive actions per minute (“goal directed”) devaluation-insensitive 5 (“habitual”)  neurally dissociable with lesions 0 (Dickinson, Balleine, Killcross) moderate extensive training training  dual systems view

  11. task 70% 70 % with prob : 26% 57% 41% 28% ( all slowly changing ) (Daw, Gershman, Seymour, et al Neuron 2011)

  12. question does choice behavior respect sequential structure?

  13. idea How does bottom-stage feedback affect top-stage choices? Example: rare transition at top level, followed by win 30% • Which top-stage action is now favored?

  14. predictions direct reinforcement model-based planning ignores transition structure respects transition structure

  15. data 17 subs x 201 trials each reward: p<1e-8 reward x rare: p<5e-5 (mixed effects logit) planning reinforcement  results reject pure reinforcement models  suggest mixture of planning and reinforcement processes (Daw, Gershman, Seymour, et al Neuron 2011)

  16. dual task single task dual task dual x reward: p < 5e-7 dual x reward x rare: p< .05 Otto, Gershman, Markman

  17. neural analysis behavior incorporates model knowledge: not just TD want to ask same question neurally can we dissociate multiple neural systems underlying neural behavior •in particular, can we show subcortical systems are dumb?

  18. dopamine & RL (Schultz et al. 1997) (Daw et al. 2011)

  19. fMRI analysis hypothesis: striatal “error” signals are solely reinforcement driven 1. generate candidate error signals assuming TD 2. additional regressor captures how this signal would be changed for errors relative to values computed by planning TD error change due to net signal forward planning + β· = estimate this

  20. fMRI analysis TD error change due to forward planning + β·  contrary to theories: even striatal error signals incorporate knowledge of task structure (Daw, Gershman, Seymour, et al Neuron 2011) (P<.05 cluster)

  21. variation across subjects subjects differ in degree of model usage change due to net signal planning = TD error + β· = compare behavioral & neural estimates

  22. variation across subjects subjects differ in degree of model usage TD error change due to net signal planning + β· = p<.05 SVC

  23. average signal R NAcc: start of trial: • interaction not significant • but size of interaction covaries with behavioral model usage (p=.02)

  24. thoughts can distinguish multiple learned representations in humans •neurally more intertwined than expected related areas: self control (drugs, dieting, savings etc.) learning in multiplayer interactions (games) •equilibrium vs equilibration •do we learn about actions or about opponents?

  25. p-beauty context • fast equilibration with repeated play, most subjects never reinforced Singaporean undergrads – Ho et al. 1998

  26. RPS • do subjects learn by reinforcement? • best respond to reinforcement? • best respond to that? (Hampton et al, 2008)

  27. conclusions 0. use of computational models to quantify phenomena & distinctions for neural study 1. can leverage this to distinguish different sorts of learning, trial-by-trial – beginning to map neural substrates 2. implications for self control, economic interactions

Recommend

10703 Deep Reinforcement Learning Reinforcement Learning in Humans and Animals Tom Mitchell

10703 Deep Reinforcement Learning Reinforcement Learning in Humans and Animals Tom Mitchell

10703 Deep Reinforcement Learning Reinforcement Learning in Humans and Animals Tom Mitchell October 29, 2018 Reading: Barto &amp; Sutton Chapter 15 Tom Mitchell, October 2018 Outline RL in primates RL in humans Error signals and

448 views • 20 slides
Science Animals Including Humans Science | Year 6 | Animals Including Humans | Transporting Water

Science Animals Including Humans Science | Year 6 | Animals Including Humans | Transporting Water

Science Animals Including Humans Science | Year 6 | Animals Including Humans | Transporting Water and Nutrients | Lesson 3 Aim I can explain how water and nutrients are transported within the body. Success Criteria I can state how the

343 views • 12 slides
TRAMADOL LETHAL DOSE HUMANS ARE ANIMALS PRESENTATION Tramadol Lethal Dose Humans Are Animals

TRAMADOL LETHAL DOSE HUMANS ARE ANIMALS PRESENTATION Tramadol Lethal Dose Humans Are Animals

TRAMADOL LETHAL DOSE HUMANS ARE ANIMALS PRESENTATION Tramadol Lethal Dose Humans Are Animals Presentation tramadol for ocd can u mix xanax with tramadol what is the difference between tramadol for pets and humans tramadol human dosage for

147 views • 3 slides
Meta Reinforcement Learning Chelsea Finn Why are humans so good at RL? People have prior

Meta Reinforcement Learning Chelsea Finn Why are humans so good at RL? People have prior

Meta Reinforcement Learning Chelsea Finn Why are humans so good at RL? People have prior experience. People have an existing representation of the world. Can we learn a representation under which RL is fast? Key idea : Explicitly optimize for

1.04k views • 41 slides
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
Science Success Criteria Aim I can name some animals that are carnivores, herbivores and

Science Success Criteria Aim I can name some animals that are carnivores, herbivores and

Year One Science | Year 1 | Animals Including Humans | What Do I Eat? | Lesson 6 Animals Including Humans Science Success Criteria Aim I can name some animals that are carnivores, herbivores and omnivores. I can sort animals into

533 views • 18 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

682 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

540 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
Ethic Analysis on Using Humans and Animals in Research Group I - IT department Problem More

Ethic Analysis on Using Humans and Animals in Research Group I - IT department Problem More

Ethic Analysis on Using Humans and Animals in Research Group I - IT department Problem More than 33 million people today have HIV and risk contracting AIDS if they do not receive effective inhibitor medications. A great deal of research is

502 views • 10 slides
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control Prashanth L.A.

Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control Prashanth L.A.

Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control Prashanth L.A. Joint work with Cheng Jie, Michael Fu, Steve Marcus and Csaba Szepesvri University of Maryland, College Park AI that benefjts humans

491 views • 20 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

More recommend