Updated and formatted README

Modified plot_improvement.py to fix agent directory sorting bug

Got config for dqn version 2.1

Updated README metadata with eval metrics. Updated README with note on replay and eval metrics

updated readme, added replay.mp4 to home directory

Updated README

Updated README

Updated README

Updated README

Updated README to display video widget

Removed unecessary comments in plot_improvement.py

Removed old code from get_config.py

Modified get_config.py. Updated README. Added config file for most recent agent.

Deleted json files from videos. Renamed video files.

Updated README. Deleted scripts under development from main branch. They are located in development branch.

updated readme

Added videos of the best model from the most recent run

Removed testing videos

Modified evaluate_agent.py slightly.

Added TB charts for agent v2.8

Added agent v2.8 and notebook

Updated README

Added framework for saving charts in plot_improvement.py

plot_improvement works OK, could use fine tuning

started using numpy like i should have to begin with...

plot improvement is a mess, but getting there

Changed the video recorder directory

Began work on plotting improvements between training runs

Added agent and notebook for dqn version 2.7

Updated ReadMe

Updated watch agent script to remove rendering option

Moved the config and watch scripts to the root directory. Split the watch script into two scripts: watch and evaluate.

Renamed pull_config to get_config. Updated get_config script, working as I'd like

Updated Readme

Added notebook and agent files for dqnv2.6

Modified plot_evaluations.py with experimental labels and scaling. Still needs more tuning.

Updated record_video.py to truncate recording upon episode end. File still saves based on steps specified, however...

Updated notes in watch_agent.py

Added functionality to watch_agent.py to support evaluating different agents.

Added pull_config.py to grab configuration data from agent. Script is still being tested and tuned.

Added checkpoint agents to each dqn version. Added the notebook for dqn 2.5

Changed file structure for agents and updated readme

Updated tags in readme file

removed example video

record_video.py now functions, needs tuning

Modified the record_video.py file, still not functional.

Added the a2c notebook and the latest dqn run notebook

Updated the agent file and best model file for version_2

Added option flags to the watch_agent.py file.

Modified watch_agent.py to include ability to give an argument to adjust repeat action probability.