Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add Parallel Q-Networks algorithm (PQN) #472

Merged
merged 10 commits into from
Nov 14, 2024
Merged

Add Parallel Q-Networks algorithm (PQN) #472

merged 10 commits into from
Nov 14, 2024

Commits on Jul 17, 2024

  1. wip

    @roger-creus
    roger-creus committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    6e89a5c View commit details
    Browse the repository at this point in the history

  2. wip

    @roger-creus
    roger-creus committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    e9f158f View commit details
    Browse the repository at this point in the history

  3. Run pre-commit run --all-files

    @roger-creus
    roger-creus committed Jul 17, 2024
    Configuration menu
    Copy the full SHA
    21226d7 View commit details
    Browse the repository at this point in the history

Commits on Jul 18, 2024

  1. each env has its own probability of random.random() < epsilon -- i.e.… 

    … some envs can explore and some exploit, like in the official implementation
    @roger-creus
    roger-creus committed Jul 18, 2024
    Configuration menu
    Copy the full SHA
    fba8994 View commit details
    Browse the repository at this point in the history

Commits on Jul 25, 2024

  1. added pqn with lstm. works on breakout :)

    @roger-creus
    roger-creus committed Jul 25, 2024
    Configuration menu
    Copy the full SHA
    b6a12c1 View commit details
    Browse the repository at this point in the history

Commits on Jul 26, 2024

  1. Use buffer for values instead of re-computing in Q(lambda). Speed up … 

    …150%
    @roger-creus
    roger-creus committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    bfe1205 View commit details
    Browse the repository at this point in the history

Commits on Oct 25, 2024

  1. Merge remote-tracking branch 'upstream/master'

    @roger-creus
    roger-creus committed Oct 25, 2024
    Configuration menu
    Copy the full SHA
    cc66288 View commit details
    Browse the repository at this point in the history

  2. default rollout hyperparameters in PQN are now equal to PPO. same for… 

    … PQN Lstm. Ran validation experiments. Reverting undesired changes in DQN. WIP documentation
    @roger-creus
    roger-creus committed Oct 25, 2024
    Configuration menu
    Copy the full SHA
    10334fa View commit details
    Browse the repository at this point in the history

Commits on Oct 31, 2024

  1. Added coumentation. Fixed links to the docs for PQN

    @roger-creus
    roger-creus committed Oct 31, 2024
    Configuration menu
    Copy the full SHA
    c8acf70 View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2024

  1. Finished PQN documentation by adding commands to run the benchmarks a… 

    …d plotting the results
    @roger-creus
    roger-creus committed Nov 14, 2024
    Configuration menu
    Copy the full SHA
    d9c300b View commit details
    Browse the repository at this point in the history