Hugging Face's logo

ledmands
/
ALE-Pacman-v5

Reinforcement Learning
stable-baselines3
TensorBoard
dqn
Reinforcement Learning
Atari
Pac-Man
Eval Results (legacy)
Model card Files
xet
 Metrics Community
ALE-Pacman-v5 / agents

Commit History

  1. Got config for dqn version 2.1

    ledmands
    2ef57f9

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

    ledmands
    df1cef8

  2. Removed testing videos

    ledmands
    956eab4

  1. Modified evaluate_agent.py slightly.

    ledmands
    7a9dcf1

  2. Added agent v2.8 and notebook

    ledmands
    f98a19f

  1. Changed the video recorder directory

    ledmands
    2690fb6

  2. Began work on plotting improvements between training runs

    ledmands
    94c3490

  1. Added agent and notebook for dqn version 2.7

    ledmands
    acd0718

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

    ledmands
    ca16748

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

    ledmands
    baeb5f8

  1. Added notebook and agent files for dqnv2.6

    ledmands
    f037205

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

    ledmands
    e64054f

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

    ledmands
    a2ff203

  4. Updated notes in watch_agent.py

    ledmands
    1427095

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

    ledmands
    a30d4ce

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

    ledmands
    866f598

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

    ledmands
    e96aefa

  8. Changed file structure for agents and updated readme

    ledmands
    c36f44f

  1. removed example video

    ledmands
    9938803

  2. record_video.py now functions, needs tuning

    ledmands
    36f3504

  3. Modified the record_video.py file, still not functional.

    ledmands
    6aec4d8

  4. Added the a2c notebook and the latest dqn run notebook

    ledmands
    e3b737c

  5. Updated the agent file and best model file for version_2

    ledmands
    3ae69be

  6. Added option flags to the watch_agent.py file.

    ledmands
    cbe0575

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

    ledmands
    c37ff18

  8. Added video recording, plotting, and viewing script templates.

    ledmands
    ebb75df

  9. Changed naming convention for agent directories and TensorBoard directories

    ledmands
    980c356

  1. Removed redundant ppo notebook

    ledmands
    bac7ebe

  2. Added PPO trial run

    ledmands
    d458235

  3. Added run2v3 to notebooks. Updated run_2 model and best model. Added run2v3 TensorBoard and eval files to agents.

    ledmands
    5f7e8a6

  1. Added second Tensorboard file from run2 to its own file in order to split it out in the Tensorboard dashboard.

    ledmands
    986734a

  2. Updated run_2 agent and best model. Added evaluations and Tensorboard files to run_2.

    ledmands
    8bb61db

  3. Added final notebook files for first runs. Added Agents and evals from first runs.

    ledmands
    9d02e54