https://github.com/timbmg/easy21-rl
Easy21 assignment from David Silver's RL Course at UCL
https://github.com/timbmg/easy21-rl
function-approximation monte-carlo reinforcement-learning reinforcement-learning-excercises rl sarsa sarsa-lambda
Last synced: 8 months ago
JSON representation
Easy21 assignment from David Silver's RL Course at UCL
- Host: GitHub
- URL: https://github.com/timbmg/easy21-rl
- Owner: timbmg
- Created: 2018-04-29T10:27:17.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-04-29T10:38:35.000Z (about 8 years ago)
- Last Synced: 2025-08-02T09:12:50.356Z (10 months ago)
- Topics: function-approximation, monte-carlo, reinforcement-learning, reinforcement-learning-excercises, rl, sarsa, sarsa-lambda
- Language: Python
- Size: 1.57 MB
- Stars: 12
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Easy21 Implementation
This is an implementation of the Easy21 assignment of David Silver's Reinforcement Learning Course at UCL. The assignment can be found [here](http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching_files/Easy21-Johannes.pdf).
## Monte-Carlo Control
`python3 mc.py`
10 Million Episodes of the game have been evaluated, to obtain the following Value function:
## TD Learning
`python3 td.py`
Mean Squared Error of the state-action function of the Monte-Carlo experiment with different Lambdas. For each lambda, 10 000 Episodes have been evaluated.
Mean Squared Error evolution with different Lambdas.
## Linear Function Approximation
`python3 lfa.py`
The lookup table of the previous experiment is replaced with a linear function approximation. The logic for the feature vector can be found in the assignment.
