Kunstmatige Intelligentie / RuG KI2 - 11 Reinforcement Learning Sander van Dijk.

Kunstmatige Intelligentie / RuG

KI2 - 11

Reinforcement Learning

Sander van Dijk

What is Learning ?

Percepts received by an agent should be used not only for acting, but also for improving the agent’s ability to behave optimally in the future to achieve its goal.

Interaction between an agent and the world

Learning Types

Supervised learning: Input, output) pairs of the function to be

learned can be perceived or are given.Back-propagation

Unsupervised Learning: No information at all about given output

SOM

Reinforcement learning: Agent receives no examples and starts with

no model of the environment and no utility function. Agent gets feedback through rewards, or reinforcement.

Reinforcement Learning

Task Learn how to behave successfully to achieve a

goal while interacting with an external environmentLearn through experience from trial and error

Examples Game playing: The agent knows it has won or

lost, but it doesn’t know the appropriate action in each state

Control: a traffic system can measure the delay of cars, but not know how to decrease it.

Elements of RL

Transition model, how action influence states Reward R, immediate value of state-action transition Policy , maps states to actions

Agent

Environment

State Reward Action

Policy

sss 221100 r a2

r a1

r a0 :::

Elements of RL

r(state, action)immediate reward values

100

0

0

100

G

0

0

0

0

0

0

0

0

0

Elements of RL

Value function: maps states to state values

Discount factor [0, 1) (here 0.9)

V*(state) valuesr(state, action)immediate reward values

100

0

0

100

G

0

0

0

0

0

0

0

0

0 G

90 100 0

81 90 100

2 11π trγtγrtrsV ...

G 90 100 0

81 90 100

G 90 100 0

81 90 100

RL task (restated)

Execute actions in environment,

observe results.

Learn action policy : state action

that maximizes expected discounted

reward

E [r(t) + r(t + 1) + 2r(t + 2) + …]

from any starting state in S

Reinforcement Learning

Target function is : state action

However… We have no training examples of form

<state, action>

Training examples are of form

<<state, action>, reward>

Utility-based agents

Try to learn V * (abbreviated V*) Perform look ahead search to choose best action

from any state s

Works well if agent knows

: state action state

r : state action R

When agent doesn’t know and r, cannot choose

actions this way

a s,δ*Va s,rmaxargsπ*a

Q-values

Q-values

Define new function very similar to V*

If agent learns Q, it can choose optimal

action even without knowing or R

Using Q

a s,δ*Va s,ra s,Q

a s,Q maxargsπ*a

Learning the Q-value

Note: Q and V* closely related

Allows us to write Q recursively as

Temporal Difference learning

a' s,Q maxargs*Va'

a' ,tsQmax γta ,tsr

ta ,tsδγVta ,tsr ta ,tsQ

a'1

Learning the Q-value

FOR each <s, a> DO

Initialize table entry:

Observe current state s

WHILE (true) DO

Select action a and execute it

Receive immediate reward r

Observe new state s’

Update table entry for as follows

Move: record transition from s to s’

0 a s,Q̂

a s,Q̂

a' ,s'Q max γa s,r a s,Q a'

ˆˆ

r(state, action)immediate reward values

Q(state, action) valuesV*(state) values

100

0

0

100

G

0

0

0

0

0

0

0

0

0

90

81

100

G

0

81

72

90

81 81

72

90

81

100

G 90 100 0

81 90 100

Q-learning

Q-learning, learns the expected utility of taking a particular action a in a particular state s (Q-value of the pair (s,a))

Representation

Explicit

Implicit Weighted linear function/neural network

Classical weight updating

State Action Q(s, a)

2 MoveLeft 81

2 MoveRight 100

... ... ...

Exploration

Agent follows policy deduced from learned Q-values

Agent always performs same action in certain state, but perhaps there is an even better action?

Exploration: Be safe <-> learn more, greed <-> curiosity.

Extremely hard, if not impossible, to obtain optimal exploration policy.

Randomly try actions that have not been tried often before but avoid actions that are believed to be of low utility

Q-learning estimates one time step difference

Why not for n steps?

a ,tsQ max γ tr ta ,tsQ a

11 ˆ

a ,ntsQ maxγntrγ tγr tr ta ,tsQ a

nnn ˆ11 1

Enhancement: Q()

Q() formula

Intuitive idea: use constant 0 1 to combine estimates from various look ahead distances (note normalization factor (1- ))

ta ,tsQλta ,tsλQta ,tsQ λ ta ,tsQ λ 32211

Enhancement: Q()

Enhancement: Eligibility Traces

Look backward instead of forward. Weigh updates by eligibility trace e(s,

a). On each step, decay all traces by and

increment the trace for the current state-action pair by 1.

Update all state-action pairs in proportion to their eligibility.

Genetic algorithms

Imagine the individuals as agent functions

Fitness function as performance measure or reward function

No attempt made to learn the relationship between the rewards and actions taken by an agent

Simply searches directly in the individual space to find one that maximizes the fitness functions

Genetic algorithms

Represent an individual as a binary string Selection works like this: if individual X scores

twice as high as Y on the fitness function, then X is twice as likely to be selected for reproduction than Y.

Reproduction is accomplished by cross-over and mutation

Cart – Pole balancing

Demonstration

http://www.bovine.net/~jlawson/hmc/pole/sane.html

Summary

RL addresses the problem of learning control strategies for autonomous agents

TD-algorithms learn by iteratively reducing the differences between the estimates produced by the agent at different times

In Q-learning an evaluation function over states and actions is learned

In the genetic approach, the relation between rewards and actions is not learned. You simply search the fitness function space.