Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / dena/handyrl issues and pull requests

#48 - (WIP) feature: policy, value (& return) target selection

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#48 - (WIP) feature: policy, value (& return) target selection

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#47 - feature: entropy_regularization_decay in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#47 - feature: entropy_regularization_decay in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#46 - feature: dict style evaluation result and gather data in Learner

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#46 - feature: dict style evaluation result and gather data in Learner

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#45 - feature: output epoch number to console

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#45 - feature: output epoch number to console

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#44 - (WIP) tensorflow v2 backend

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#44 - (WIP) tensorflow v2 backend

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#43 - chore: fix styles

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#43 - chore: fix styles

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#42 - feature: save latest model

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#42 - feature: save latest model

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#41 - (Important) update: main file and handyrl directory

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#41 - (Important) update: main file and handyrl directory

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#40 - feature: send batch data to batcher (not per episode)

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#40 - feature: send batch data to batcher (not per episode)

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#39 - Add player argument to Agent class in evaluation.py

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#39 - Add player argument to Agent class in evaluation.py

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#38 - (WIP) rulebase AI for Geister

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 3 comments

#38 - (WIP) rulebase AI for Geister

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 3 comments

#37 - Experiment/no layer dimension

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#37 - Experiment/no layer dimension

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#36 - action index different for each player, especially for symmetric environment

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#36 - action index different for each player, especially for symmetric environment

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#35 - fix: forword computation of RNN in training

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 2 comments

#35 - fix: forword computation of RNN in training

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 2 comments

#34 - feature: compress steps in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#34 - feature: compress steps in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#33 - update: load model with strict=False

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#33 - update: load model with strict=False

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#32 - feature: update network style of Geister

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#32 - feature: update network style of Geister

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#31 - update: lambda in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#31 - update: lambda in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#30 - feature: parallel action selection

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#30 - feature: parallel action selection

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#29 - chore: rename HandyDistributedRL to HandyRL

Pull Request - State: closed - Opened by ikki407 about 4 years ago

#29 - chore: rename HandyDistributedRL to HandyRL

Pull Request - State: closed - Opened by ikki407 about 4 years ago

#28 - update: batch_first style for using nn.DataParallel

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 4 comments

#28 - update: batch_first style for using nn.DataParallel

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 4 comments

#27 - feature: enable to load partial model

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#26 - feature: add restart_epoch in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#26 - feature: add restart_epoch in config.yaml

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#25 - fix: load batch on GPU in trainer's main thread

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#25 - fix: load batch on GPU in trainer's main thread

Pull Request - State: closed - Opened by YuriCat about 4 years ago - 1 comment

#24 - Minor updates

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#24 - Minor updates

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#23 - immediate rewards / terminal outcomes dual targets

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 2 comments

#23 - immediate rewards / terminal outcomes dual targets

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 2 comments

#22 - Bugfix: training recurrent networks

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#21 - Adapt immediate reward setting

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 2 comments

#21 - Adapt immediate reward setting

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 2 comments

#20 - Compress and decompress step by step

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#20 - Compress and decompress step by step

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#19 - Update: use batcher process in default setting

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#19 - Update: use batcher process in default setting

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#18 - update: callback functions in Batcher as member function

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#18 - update: callback functions in Batcher as member function

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#17 - FIX: get player indices of model_id from env.players()

Pull Request - State: closed - Opened by ikki407 over 4 years ago

#17 - FIX: get player indices of model_id from env.players()

Pull Request - State: closed - Opened by ikki407 over 4 years ago

#16 - Fix for Python3.8 and small updates

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#16 - Fix for Python3.8 and small updates

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#15 - Fix player name in README.md and environment.py

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 1 comment

#14 - [RE-CREATE] Add battle loop test of environments as github actions

Pull Request - State: closed - Opened by ikki407 over 4 years ago - 1 comment

#13 - Add battle loop test of environments as github actions

Pull Request - State: closed - Opened by ikki407 over 4 years ago - 1 comment

#12 - Update new version

Pull Request - State: closed - Opened by YuriCat over 4 years ago - 3 comments

#11 - [WIP] Update/Multi Role Worker

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#10 - Remove unused continue/shutdown boolean flag between server and workers

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#9 - [WIP] test/default input array

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#8 - Remove non-ascii comment from environments/tictactoe.py

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#7 - Remove unused function from train.py

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#6 - Change tuple with list in ConvLSTMCell.init_hidden()

Pull Request - State: closed - Opened by ikki407 over 4 years ago

#5 - Remove unused tensor conversion functions from generation.py

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#4 - Remove non-ascii suffix that express first or second player

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#3 - Remove daemon flags of threads

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#2 - Remove unused debug function

Pull Request - State: closed - Opened by YuriCat over 4 years ago

#1 - Finish threads by wrapping by 'try: finally:'

Pull Request - State: closed - Opened by yukohno over 4 years ago