Click here to Skip to main content
15,437,139 members

Articles by philoxenic (Articles: 13)

Articles: 13

RSS Feed

Average article rating: 4.87

Artificial Intelligence
Machine Learning
25 Jun 2020   Updated: 25 Jun 2020   Rating: 3.26/5    Votes: 9   Popularity: 3.11
Licence: CPOL    Views: 7,822     Bookmarked: 6   Downloaded: 0
Please Sign up or sign in to vote.
In this article, you will be up and running, and will have done your first piece of reinforcement learning.
26 Jun 2020   Updated: 26 Jun 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 4,084     Bookmarked: 0   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we will see what’s going on behind the scenes and what options are available for changing the reinforcement learning.
29 Jun 2020   Updated: 29 Jun 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 10,647     Bookmarked: 3   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we start to look at the OpenAI Gym environment and the Atari game Breakout.
30 Jun 2020   Updated: 30 Jun 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 5,276     Bookmarked: 4   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we will see how you can use a different learning algorithm (plus more cores and a GPU) to train much faster on the mountain car environment.
2 Jul 2020   Updated: 2 Jul 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 5,144     Bookmarked: 2   Downloaded: 0
Please Sign up or sign in to vote.
In this article we will learn from the contents of the game’s RAM instead of the pixels.
3 Jul 2020   Updated: 3 Jul 2020   Rating: 5.00/5    Votes: 1   Popularity: 0.00
Licence: CPOL    Views: 4,062     Bookmarked: 2   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we will see how we can improve by approaching the RAM in a slightly different way.
6 Jul 2020   Updated: 6 Jul 2020   Rating: 5.00/5    Votes: 1   Popularity: 0.00
Licence: CPOL    Views: 3,941     Bookmarked: 1   Downloaded: 0
Please Sign up or sign in to vote.
In this final article in this series, we will look at slightly more advanced topics: minimizing the "jitter" of our Breakout-playing agent, as well as performing grid searches for hyperparameters.
25 Sep 2020   Updated: 25 Sep 2020   Rating: 5.00/5    Votes: 4   Popularity: 3.01
Licence: CPOL    Views: 5,292     Bookmarked: 8   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we set up with the Bullet physics simulator as a basis for doing some reinforcement learning in continuous control environments.
28 Sep 2020   Updated: 28 Sep 2020   Rating: 5.00/5    Votes: 1   Popularity: 0.00
Licence: CPOL    Views: 6,762     Bookmarked: 4   Downloaded: 0
Please Sign up or sign in to vote.
In this article, we look at two of the simpler locomotion environments that PyBullet makes available and train agents to solve them.
29 Sep 2020   Updated: 29 Sep 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 5,562     Bookmarked: 2   Downloaded: 0
Please Sign up or sign in to vote.
In this article in the series we start to focus on one particular, more complex environment that PyBullet makes available: Humanoid, in which we must train a human-like agent to walk on two legs.
30 Sep 2020   Updated: 30 Sep 2020   Rating: 5.00/5    Votes: 2   Popularity: 1.51
Licence: CPOL    Views: 4,372     Bookmarked: 3   Downloaded: 0
Please Sign up or sign in to vote.
In this article we will adapt our code to train the Humanoid environment using a different algorithm: Soft Actor-Critic (SAC).
1 Oct 2020   Updated: 1 Oct 2020   Rating: 5.00/5    Votes: 3   Popularity: 2.39
Licence: CPOL    Views: 3,961     Bookmarked: 3   Downloaded: 0
Please Sign up or sign in to vote.
In this article we will try to train our agent to run backwards instead of forwards.
2 Oct 2020   Updated: 2 Oct 2020   Rating: 5.00/5    Votes: 2   Popularity: 1.51
Licence: CPOL    Views: 3,793     Bookmarked: 2   Downloaded: 0
Please Sign up or sign in to vote.
In article in this series we will look at even deeper customisation: editing the XML-based model of the figure and then training the result.

Average blogs rating:

No blogs have been submitted.

Average tips rating:

No tips have been posted.

Average reference rating:

No reference articles have been posted.

Average project rating:

No projects have been posted.
Web Developer
United Kingdom United Kingdom
This member has not yet provided a Biography. Assume it's interesting and varied, and probably something to do with programming.