Comments (1)
Generally π is any probability distribution. If there is only one optimal action, optimal policy must deterministically choose that action. If there are multiple optimal actions, the optimal policy can be any distribution over them. I added a note to the slide saying that in case of multiple actions minimizing q_*(s, a), the policy can stochastically choose any of them.
from npfl122.
Related Issues (14)
- Parameter to change for UCB in MultiArmedBandits seems wrong HOT 1
- Lecture 1 / slide 14: Fixed learning rate vs alpha_n HOT 1
- S^+ not explained in code HOT 1
- Make the possibility of obtaining various rewards from the same transition more explicit HOT 3
- Lecture 9 / Slide 16 text doesn't fit inside HOT 1
- "The gradient direction is a local minimizer" HOT 1
- PopArt - is 'n' really unnormalized? HOT 1
- Missing `import math` in wrappers.py in 03 labs HOT 1
- TD errors definitions +-1 error HOT 2
- Non-matching types HOT 1
- Using f-string instead of `str.format()` HOT 1
- Possible typo HOT 3
- [06/slides] Wrong/misleading pseudocode for REINFORCE HOT 1
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 npfl122.