dalmia / david-silver-reinforcement-learning Goto Github PK
View Code? Open in Web Editor NEWNotes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.
License: MIT License
Notes for the Reinforcement Learning course by David Silver along with implementation of various algorithms.
License: MIT License
The codes Blackjack_playground.ipynb and model_free_prediction both contains a part of code in the starting
import sys
if "../" not in sys.path:
.. sys.path.append("../")
from lib.envs.blackjack import BlackjackEnv
from lib import plotting
env = BlackjackEnv()
This part of the code gives error "ImportError: "lib" not found". This is because Denny Britz used a different file structure for module placement. The correct version for any general user should be:
Step1: Add plotting.py file from "Denny Britz" library in the same folder as the codes.
Step2 : corrections in code:
import gym
from plotting import *
env=gym.make('Blackjack-v0')
the code of the example of DP (chapter 3 ), do not run the part of value iteraion because in line 209 you pass the action_values but is necesary to pass V.
action_values = one_step_lookahead(environment, state, V, discount_factor)
I checked out the frozen lake source code in the open ai gym repo https://github.com/openai/gym/blob/master/gym/envs/toy_text/frozen_lake.py and its mentioned here that:
LEFT = 0
DOWN = 1
RIGHT = 2
UP = 3
But in frozen_lake.py:
0: '\u2191', # UP
1: '\u2192', # RIGHT
2: '\u2193', # DOWN
3: '\u2190', # LEFT
I think it should be:
0: '\u2190', # LEFT
1: '\u2193', # DOWN
2: '\u2192', # RIGHT
3: '\u2191', # UP
Please clear the confusion and let me know.
Update the PDF Links one by one using this as the link start. The PDF names remain the same.
Eg :
Lec 7 : Policy Gradient (pg.pdf)
https://www.davidsilver.uk/wp-content/uploads/2020/03/pg.pdf
Lec 6 : Value Function Approximation (FA.pdf)
https://www.davidsilver.uk/wp-content/uploads/2020/03/FA.pdf
pdf takes minutes to download. Are there different links that are faster?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.