Comments (4)
Figure 4.1 is only policy evaluation not policy iteration, so we should not change the random policy. And even you do policy iteration I do not see any reason to use a softmax, unless you are working on soft q-learning. https://arxiv.org/abs/1704.06440
from reinforcement-learning-an-introduction.
So, by changing the action probabilities I am doing policy iteration
, and using softmax is not the right way?
from reinforcement-learning-an-introduction.
yes
from reinforcement-learning-an-introduction.
Hey I came to a realization that for it to be a policy iteration it must satisfy this one
- Initialization
V (s) ∈ R and π(s) ∈ A(s) arbitrarily for all s ∈ S - Policy Evaluation
Repeat
∆ ← 0
For each s ∈ S:
v ← V (s)
V (s) ← s ,r p(s , r |s, π(s)) r + γV (s )
∆ ← max(∆, |v − V (s)|)
until ∆ < θ (a small positive number) - Policy Improvement
policy-stable ← true
For each s ∈ S:
old-action ← π(s)
π(s) ← argmax a s ,r p(s , r |s, a) r + γV (s )
If old-action = π(s), then policy-stable ← f alse
If policy-stable, then stop and return V ≈ v ∗ and π ≈ π ∗ ; else go to 2
We should have a separate policy evaluation succeeded by one policy improvement,
but it seems that what I did on my code was value iteration, this one
Repeat
∆ ← 0
For each s ∈ S:
v ← V (s)
V (s) ← max a s ,r p(s , r |s, a) r + γV (s )
∆ ← max(∆, |v − V (s)|)
until ∆ < θ (a small positive number)
Output a deterministic policy, π ≈ π ∗ , such that
π(s) = argmax a s ,r p(s , r |s, a) r + γV (s )
here I used softmax as a probability value of each action.
from reinforcement-learning-an-introduction.
Related Issues (20)
- Unable to get the same results while formulating differently HOT 1
- A simpler draw function HOT 2
- nit: chapter 6 references
- something wrong in matplotlib HOT 2
- Generalization to abstract classes for Environment/Agents? HOT 2
- tictactoe compete() plays 1000 almost identical games HOT 1
- typo
- wrong figure number for chapter 11
- ten_armed_testbed.py中的figure2_3为何不用“sample_averages”
- problem about chapter04/car_rental.py HOT 1
- example to use it on human genetic data?
- Problem of excercise 2.5
- The plicy of chapter1 HOT 1
- Wrong Bellman equation for Jack's car rental problem? HOT 1
- Unclear point for the code in Blackjack example HOT 1
- l
- ch06 random_walk td method HOT 1
- chapter4 gamblers_problem, showing multiple best actions
- Chapter 2: Couldn't find the file '../images/figure_2_1.png'
- Citing this repository
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from reinforcement-learning-an-introduction.