Structured prediction with reinforcement learning

Structured Prediction With Reinforcement Learning

Guruprasad Zapate

University of Paderborn

1

Outline● Introduction

○ Structured Prediction (SP)

○ Reinforcement Learning (RL)

● SP-MDP framework

● Approximated RL Algorithms

● Conclusion

2

Structured Prediction (SP)● In “normal” machine learning our goal is to learn unknown function

➔ Here input can be any kind of complex objects

➔ And output is a real value number

◆ For e.g classification, regression, density estimation

● Structure Prediction goal is to learn such that:

➔ Where outputs are structured objects

3

Structured Prediction(SP)● Structured data :

○ “Data that consists of several parts, and not only the parts themselves contain information, but also

the way in which the parts belong together.”

● Texts, images, documents etc. are type of structured data

Text

4 Image Source

Structured Prediction(SP)● SP has wide applications in the various AI fields such as:

○ Natural Language Processing

○ Images and video processing

○ Speech Processing

○ Bioinformatics

5

Image Source

Semantic Image Segmentation Spam Filtering

Structured Prediction(SP)● Models used to solve SP problems

○ Global Models

■ Focuses on the global characteristics of the data

■ For simplicity classification is also used

■ Linear models such as Perceptron, SVM are customized for structured outputs

■ Conditional Random Fields(CRF) are also widely used

○ Incremental Models

■ Turn learning into sequential process

■ After each step partial output is predicted and model is updated

■ Incremental Parsing, Incremental Prediction are some the few models which uses

incremental approach

6

Reinforcement Learning (RL)● A type of Machine Learning with core idea :

○ To make machines as intelligent as humans, we need to make machines learn like humans

● Learning model contains following entities:

○ Agent (Decision Maker/Learner)

○ Environment (External conditions)

○ States

○ Actions

○ Rewards - the consequence of actions

● Agent learns from interaction with environment through the means of reward

7

Reinforcement Learning (RL)

● Learning procedure in RL

○ Agent observes a state

○ An action is determined by a decision making function (policy)

○ Action is performed and state is changed

○ Reward function assigns rewards from the environment

● Two distinguish characteristics

○ Trial & Error Search

○ Delayed Rewards

8Image Source

MDP Framework● Markov Decision Processes formally describes an environment for RL

● Processes hold Markov property which states:

○ “The future is independent of the past given the present”

● MDP framework contains following components:

○ Set of possible states S○ Set of possible actions A○ A real valued reward function R(s,a)○ State Transition function T to measure each action’s effect in each state

● Next state is only dependent on the current state, past states are insignificant

● Goal is to find an optimal policy that maximizes the total reward

9

SP-MDP Framework ● Structured Prediction Markov Decision Process (SP-MDP)

○ Instantiation of MDP for Structured Prediction

● SP-MDP framework constitutes of following components:

○ States

■ Contains both input and partial output

■ Final states contain complete output

○ Actions

■ Each state has a set of available actions

○ Transition

■ Replaces the partial output by the transformed partial output

○ Rewards

■ Loss function is used to assign rewards for state-action pair

10

SP-MDP Framework

11Image Source

Handwritten digit recognition on sequential data

SP-MDP Framework ● Rewards Integration

○ Per-episode rewards :

■ Only final states are considered for rewards

■ Final reward is negative loss of the predicted output to the correct output

○ Per-decision rewards :

■ Rewards are given after each step for all the states

■ Much richer reward signals

12

Optimal Policy in SP-MDP● Per-episode Rewards

○ Total Reward in one trajectory (state-action sequence from start to finish) for a policy

○ Optimal policy is the one which minimizes the rewards ( due to negative loss)

13

Optimal Policy in SP-MDP● Per-decision Rewards

○ Total Reward in one trajectory for a policy

○ Optimal policy is the one which minimizes the rewards

14

Equivalence between SP and SP-MDP● Learning goal in SP is to minimize the empirical risk

○ Empirical risk measures how much, on average, it hurts to use inferred function as our prediction

algorithm

○ Given parameters and loss function , goal is to minimize the loss

● Minimizing the empirical risk in SP is similar to finding optimal policy in

SP-MDP

● Equivalence helps to use RL algorithms for SP through SP-MDP framework

15

Approximated Value based RL● Quite straightforward approach

● Uses action-value function that assigns the scores for the taken actions

● Employs greedy policy to maximize the score which is defined as

● Discounted rewards are also used which determines current value of the future

rewards

● Linear functions are used for approximation for large MDPs

16

Approximated Value based RL

● SARSA, Q-Learning etc. are widely used value based RL models

● Works well in many applications

● Limitations :

○ Focused on deterministic policies

○ Small change in estimated value can affect the performance

○ Difficult to converge to a policy

○ Very complex in cases of large MDPs

17

Policy gradient RL

● Modify policy parameters directly instead of estimating action values

● Search directly for the optimal policy

● Estimates gradient through simulation

● After each step gradient is updated and stochastic ascent performed on

parameters

● Maximizes the expected reward-per-step

18

Policy gradient RL ● Advantages:

○ Better convergence properties

○ Effective in high–dimensional or continuous action spaces

○ Policy subspace can be chosen according to the task

○ Can learn stochastic policies

● Limitations:

○ Evaluating a policy is typically inefficient and high variance

○ Tends to converge to a local optimum rather than global optimum

19

Using RL algorithms in SP-MDP● Policy is learned in an SP-MDP based on any approximated RL algorithms

● Use policy for inference

● Start with an input and default initial output

● Actions are chosen using linear approximation

● Final states provide complete predicted output

● Complexity for prediction can be given as where:

○ T : maximum number of steps to predict complete output

○ : mean number of available actions

20

Conclusion● We learned & discussed topics

○ Structured Prediction

○ Reinforcement Learning

● Introduced a new framework SP-MDP that links SP & RL

● Introduced widely used RL algorithms

● Discussed how RL algorithms can be used in SP-MDP

21

Q&A● ??!

22