Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ledmands
/
ALE-Pacman-v5
like
1
Reinforcement Learning
stable-baselines3
TensorBoard
dqn
Reinforcement Learning
Atari
Pac-Man
Eval Results
arxiv:
1312.5602
License:
mit
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Use this model
main
ALE-Pacman-v5
4.73 GB
2 contributors
History:
68 commits
ledmands
Updated and formatted README
35a7301
over 1 year ago
agents
Got config for dqn version 2.1
over 1 year ago
charts
Added TB charts for agent v2.8
over 1 year ago
notebooks
Added agent v2.8 and notebook
over 1 year ago
videos
Deleted json files from videos. Renamed video files.
over 1 year ago
.gitattributes
Safe
1.56 kB
removed example video
over 1 year ago
LICENSE
Safe
1.16 kB
Added license
over 1 year ago
README.md
Safe
19 kB
Updated and formatted README
over 1 year ago
evaluate_agent.py
Safe
3.14 kB
Modified evaluate_agent.py slightly.
over 1 year ago
get_config.py
Safe
1.05 kB
Removed old code from get_config.py
over 1 year ago
plot_improvement.py
Safe
1.37 kB
Modified plot_improvement.py to fix agent directory sorting bug
over 1 year ago
replay.mp4
1.46 MB
xet
updated readme, added replay.mp4 to home directory
over 1 year ago
watch_agent.py
Safe
2.13 kB
Updated watch agent script to remove rendering option
over 1 year ago
