chainer/chainerrl issues and pull requests

#613 - Create a copy of agent in evaluation for chainerrl/experiements/train_agent_async.py

Pull Request - State: open - Opened by CyanFi over 3 years ago

#612 - Regarding the output of DQN

Issue - State: open - Opened by KitanoFumiya over 3 years ago - 1 comment

#611 - Adds links to PFRL and JMLR paper

Pull Request - State: closed - Opened by prabhatnagarajan over 3 years ago - 2 comments

#610 - ChainerRL Paper Results

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

#609 - Updates BibTeX to JMLR paper

Pull Request - State: closed - Opened by prabhatnagarajan over 3 years ago - 2 comments

#608 - Uses posix to avoid path issues for windows users

Pull Request - State: closed - Opened by prabhatnagarajan about 4 years ago - 6 comments

#607 - Updates contributing MD with dev-requirements install command

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

#606 - Fixes flake errors

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

#605 - Fixes PFN CI tests

Pull Request - State: closed - Opened by prabhatnagarajan about 4 years ago - 26 comments

#604 - What's does the columns in scores.txt mean?

Issue - State: closed - Opened by Nina-9519 about 4 years ago - 1 comment

#603 - AdditiveGaussian Overflow

Issue - State: closed - Opened by mcmips about 4 years ago

#602 - RuntimeError: CUDA environment is not correctly set up

Issue - State: closed - Opened by THSWind about 4 years ago - 3 comments

#601 - Downloading pretrained DQN models gives error: HTTP Error 403: Forbidden

Issue - State: closed - Opened by aguamentiPatronum over 4 years ago - 2 comments

#600 - SARSA missing on GitHub page and API description is incorrect?

Issue - State: closed - Opened by MieszkoFerens over 4 years ago - 3 comments

#599 - (How to) Provide a random agent for evaluation

Issue - State: closed - Opened by Pit-Storm over 4 years ago - 1 comment

#598 - Question: How to create a model which takes two inputs?

Issue - State: closed - Opened by HadiSDev over 4 years ago - 1 comment

#597 - Tensorboard support

Issue - State: closed - Opened by Ujwal2910 over 4 years ago - 2 comments

#596 - Basic Script Fix

Pull Request - State: closed - Opened by prabhatnagarajan over 4 years ago - 6 comments

#595 - TRPO Doc Fix

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

#594 - Can I get the distortion data in MujoCo?

Issue - State: open - Opened by KitanoFumiya over 4 years ago

#593 - I want to know delta in TRPO

Issue - State: open - Opened by KitanoFumiya almost 5 years ago

#592 - Fix CI errors due to pyglet, zipp, mock, and gym

Pull Request - State: closed - Opened by muupan almost 5 years ago - 14 comments
Labels: test

#591 - Update the version to 0.8.0

Pull Request - State: closed - Opened by muupan almost 5 years ago - 4 comments

#588 - What do 'agent.save' mean??

Issue - State: closed - Opened by KitanoFumiya almost 5 years ago - 5 comments

#581 - Adds proper A3C scores

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 2 comments
Labels: example

#580 - Corrects Rainbow Results

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 2 comments
Labels: example

#576 - Typo fix in CI comment.

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 2 comments
Labels: test

#575 - Run slow tests with flexCI

Pull Request - State: closed - Opened by muupan about 5 years ago - 2 comments
Labels: test

#569 - Use attrs<19.2.0 with pytest

Pull Request - State: closed - Opened by muupan about 5 years ago - 1 comment
Labels: test

#565 - Releases trained models for all reproduced agents

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 26 comments
Labels: enhancement, example

#564 - Removes GPU option from README

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 4 comments
Labels: example

#554 - decrease amount of decimal digits required to 4

Pull Request - State: closed - Opened by marioyc about 5 years ago - 2 comments
Labels: test

#552 - Corrects Scores in Examples

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 2 comments
Labels: example

#551 - Add trained models

Issue - State: closed - Opened by prabhatnagarajan about 5 years ago - 2 comments

#550 - Increase flexCI's time limit to 20min

Pull Request - State: closed - Opened by muupan about 5 years ago - 2 comments
Labels: test

#549 - Improves formatting of IQN training times

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 6 comments
Labels: example

#548 - Update train_a3c.py

Pull Request - State: closed - Opened by xinyuewang1 about 5 years ago - 2 comments
Labels: example

#547 - Update train_a3c.py

Pull Request - State: closed - Opened by xinyuewang1 about 5 years ago - 2 comments
Labels: example

#546 - Rainbow Scores

Pull Request - State: closed - Opened by prabhatnagarajan about 5 years ago - 14 comments
Labels: example

#543 - Adds List of Batch Agents to the README

Pull Request - State: closed - Opened by prabhatnagarajan over 5 years ago - 2 comments
Labels: documentation

#541 - fix function call

Pull Request - State: closed - Opened by marioyc over 5 years ago - 6 comments
Labels: bug

#540 - Improve parameter distributions used in TestGaussianDistribution

Pull Request - State: closed - Opened by muupan over 5 years ago - 4 comments
Labels: test

#539 - Use get_device_from_id since get_device is deprecated

Pull Request - State: closed - Opened by muupan over 5 years ago
Labels: enhancement

#538 - Avoid cupy.zeros_like with numpy.ndrray

Pull Request - State: closed - Opened by muupan over 5 years ago
Labels: enhancement

#537 - Use cupyx.scatter_add instead of cupy.scatter_add

Pull Request - State: closed - Opened by muupan over 5 years ago - 2 comments
Labels: enhancement

#536 - Use Link.cleargrads instead of Link.zerograds in REINFORCE

Pull Request - State: closed - Opened by muupan over 5 years ago - 4 comments
Labels: enhancement

#526 - Remove a tailing space of DoubleIQN

Pull Request - State: closed - Opened by muupan over 5 years ago
Labels: test

#525 - Adds checkpoint frequencies for serial and batch Agents.

Pull Request - State: closed - Opened by prabhatnagarajan over 5 years ago - 4 comments
Labels: enhancement

#524 - Add policy loss to TD3's logged statistics

Pull Request - State: closed - Opened by ummavi over 5 years ago
Labels: enhancement

#521 - Fixes a comment in PPO example

Pull Request - State: closed - Opened by prabhatnagarajan over 5 years ago
Labels: example

#518 - Prioritized Double IQN

Pull Request - State: closed - Opened by prabhatnagarajan over 5 years ago - 10 comments
Labels: enhancement