ledmands
/

ALE-Pacman-v5

Reinforcement Learning

stable-baselines3

Reinforcement Learning

Model card Files Files and versions Metrics Training metrics Community

ALE-Pacman-v5 / agents

2 contributors

History: 25 commits

ledmands

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

ca16748 6 months ago

a2c
Added the a2c notebook and the latest dqn run notebook 6 months ago
dqn_v1
Added the a2c notebook and the latest dqn run notebook 6 months ago
dqn_v2-1
Added checkpoint agents to each dqn version. Added the notebook for dqn 2.5 6 months ago
dqn_v2-2
Added checkpoint agents to each dqn version. Added the notebook for dqn 2.5 6 months ago
dqn_v2-3
Added checkpoint agents to each dqn version. Added the notebook for dqn 2.5 6 months ago
dqn_v2-4
Changed file structure for agents and updated readme 6 months ago
dqn_v2-5
Added checkpoint agents to each dqn version. Added the notebook for dqn 2.5 6 months ago
dqn_v2-6
Moved the config and watch scripts to the root directory. Split the watch script into two scripts: watch and evaluate. 6 months ago
ppo
Removed redundant ppo notebook 6 months ago
videos
Updated record_video.py to truncate recording upon episode end. File still saves based on steps specified, however... 6 months ago
plot_evaluations.py

1.53 kB

Modified plot_evaluations.py with experimental labels and scaling. Still needs more tuning. 6 months ago
record_video.py

1.79 kB

Updated record_video.py to truncate recording upon episode end. File still saves based on steps specified, however... 6 months ago