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.

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

Render history #149

Open
wants to merge 105 commits into
base: master
Choose a base branch
from
Open

Render history #149

wants to merge 105 commits into from

Conversation

egafni
Copy link

@egafni egafni commented Apr 15, 2021

Provides a way to store the rendered history for visualization in jupyter notebooks. If this looks reasonable to you i can clean it up for other games

werner-duvaud and others added 30 commits February 22, 2020 23:36
It seems the support variable is a long not a float
Co-authored-by: ahainaut <59559236+ahainaut@users.noreply.github.com>
…play

Prioritized replay and fix target value
werner-duvaud and others added 30 commits August 14, 2020 21:53
Co-authored-by: ahainaut <59559236+ahainaut@users.noreply.github.com>
…ner-duvaud#104)

Updated strings passted to SummaryWriter.add_scalar removing
spaces and replacing with underscores. Fixes werner-duvaud#92.
…d#105)

Added a small sub-routine that scans for previously
saved models. These can be loaded by simply selecting
the menu option instead of providing the full path.
The menu is presented in reverse chronological order
and the final option "Specify paths manually" preserves
the ability to provide a full path for the checkpoint
and replay buffer as was done previously.
because player[i-1] got reward[i] in GameHistory
…sign_in_compute_target_value

fix reward sign in compute_target_value()
…ple_n_games_at_one_time_in_get_batch

sample N games at one time in replay_buffer
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.