Skip to content

Instantly share code, notes, and snippets.

Patrick Coady pat-coady

Block or report user

Report or block pat-coady

Hide content and notifications from this user.

Learn more about blocking users

Contact Support about this user’s behavior.

Learn more about reporting abuse

Report abuse
View GitHub Profile
@pat-coady
pat-coady / ant.ipynb
Last active Aug 17, 2017
OpenAI Gym Ant (Quadruped)
View ant.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / hopper.ipynb
Last active Aug 17, 2017
OpenAI Gym Hopper
View hopper.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / half_cheetah.ipynb
Last active Aug 17, 2017
OpenAI Gym HalfCheetah
View half_cheetah.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / inverted_double_pendulum.ipynb
Last active Aug 17, 2017
OpenAI Gym InvertedDoublePendulum
View inverted_double_pendulum.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / inverted_pendulum.ipynb
Last active Aug 17, 2017
OpenAI Gym InvertedPendulum
View inverted_pendulum.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / reacher.ipynb
Last active Aug 17, 2017
OpenAI Gym Reacher
View reacher.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / README.md
Last active Aug 17, 2017
Proximal Policy Optimization with Generalized Advantage Estimation
View README.md

Proximal Policy Optimization with Generalized Advantage Estimation

By Patrick Coady: Learning Artificial Intelligence

Summary

The same learning algorithm was used to train agents for each of the ten OpenAI Gym MuJoCo continuous control environments. The only difference between evaluations was the number of episodes used per training batch, otherwise all options were the same. The code is available in the GitHub repository. The exact code used to generate the submissions is in the aigym_evaluation branch.

The README.md file in the GitHub repository provides additional details on the algorithm and usage instructions.

@pat-coady
pat-coady / predict_and_saliency.ipynb
Last active Aug 17, 2017
Tiny ImageNet: view images, predictions, and saliency maps
View predict_and_saliency.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / kernel_viz_conv4.ipynb
Last active Aug 17, 2017
Visualize Convolutional Neural Net (CNN) filters
View kernel_viz_conv4.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@pat-coady
pat-coady / racetrack_sarsa.ipynb
Last active Aug 17, 2017
Sutton and Barto Racetrack: Sarsa
View racetrack_sarsa.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
You can’t perform that action at this time.