Ecosyste.ms: Issues

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

GitHub / pfnet/pfrl issues and pull requests

#183 - DDQN Loading Issue - training not resuming properly

Issue - State: closed - Opened by jmribeiro over 1 year ago - 12 comments

#100 - Suppress flake8 E741

Issue - State: closed - Opened by muupan almost 4 years ago

#99 - Suppress flake8 E402 errors

Issue - State: closed - Opened by muupan almost 4 years ago

#98 - Adds env_stats to record_tb_stats

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

#97 - add tensorboard to the requirements.txt

Pull Request - State: closed - Opened by peasant98 almost 4 years ago - 3 comments

#96 - Fetch on updated branch

Pull Request - State: closed - Opened by watakandai almost 4 years ago

#94 - [Feature Request/Proposal] use MLFlow option or best practice of experiments management

Issue - State: open - Opened by Chachay almost 4 years ago - 1 comment
Labels: enhancement

#93 - Updates install rst

Pull Request - State: closed - Opened by prabhatnagarajan almost 4 years ago - 2 comments
Labels: documentation

#92 - Performance comparison with another popular RL library

Issue - State: closed - Opened by DrJimFan about 4 years ago - 2 comments

#91 - Migrates or remove tests with @pytest.mark.skip

Issue - State: open - Opened by prabhatnagarajan about 4 years ago

#90 - Adds isort to Contributing.md

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

#89 - Fix the hang in `train_agent_async` with Tensorboard

Pull Request - State: closed - Opened by g-votte about 4 years ago - 9 comments
Labels: bug

#87 - Dev/kandai/add success eval func

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

#86 - Add `step_hooks` and `optimizer_step_hooks` to actor-learner

Pull Request - State: closed - Opened by belldandyxtq about 4 years ago - 10 comments
Labels: enhancement

#85 - Integration of PFRL with Deep Graph Library

Issue - State: closed - Opened by eladmw about 4 years ago - 5 comments

#84 - Hindsight Experience Replay Buffer

Pull Request - State: open - Opened by prabhatnagarajan about 4 years ago - 22 comments

#83 - Set stats type

Pull Request - State: closed - Opened by marioyc about 4 years ago - 3 comments
Labels: enhancement

#82 - Adopt isort to format import sentences

Pull Request - State: closed - Opened by muupan about 4 years ago - 2 comments
Labels: testing

#81 - Detach greedy_actions before calling cpu()

Pull Request - State: closed - Opened by muupan about 4 years ago - 3 comments
Labels: bug

#80 - Eval stats collector

Pull Request - State: closed - Opened by prabhatnagarajan about 4 years ago - 10 comments
Labels: enhancement

#79 - Recurrent model with two types of inputs [question]

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

#78 - Support for Multiple GPUs

Issue - State: closed - Opened by peasant98 about 4 years ago - 1 comment

#77 - Log success rate of HIRO during evaluation with tensorboard

Pull Request - State: closed - Opened by peasant98 about 4 years ago

#76 - loading optimizer parameters

Issue - State: closed - Opened by tkelestemur about 4 years ago - 2 comments

#75 - Add use_tensorboard option to batch training

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

#74 - [WIP] MDQN

Pull Request - State: open - Opened by marioyc about 4 years ago - 1 comment

#73 - Add fetch env

Pull Request - State: closed - Opened by peasant98 about 4 years ago

#72 - About training time

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

#71 - Makes common write_header function

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

#70 - Updates the supported Python version in the README

Pull Request - State: closed - Opened by prabhatnagarajan about 4 years ago - 8 comments
Labels: documentation

#69 - Double IQN

Pull Request - State: closed - Opened by cross32768 about 4 years ago - 11 comments

#68 - Memory leak (?) when run without a GPU

Issue - State: open - Opened by tadashiK about 4 years ago - 2 comments

#67 - [DO NOT MERGE] Update README.md

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

#66 - Activate auto assign only when a PR is opened

Pull Request - State: closed - Opened by muupan about 4 years ago - 1 comment
Labels: testing

#65 - [DO NOT MERGE] Update README.md

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

#64 - Replace nn.functional.tanh with torch.tanh

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

#63 - [DO NOT MERGE] Update README.md

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

#62 - Enable auto review assignment for PRs from forks

Pull Request - State: closed - Opened by muupan about 4 years ago - 1 comment
Labels: testing

#61 - [DO NOT MERGE] Update README.md

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

#60 - [DO NOT MERGE] Update README.md

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

#59 - [DO NOT MERGE] Update auto_assign.yml

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

#58 - Fixes typo in TRPO docstring

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

#56 - add use_shared_memory option

Pull Request - State: closed - Opened by shu65 about 4 years ago - 5 comments

#55 - Save and load a module trained with DataParallel or DistributedDataParallel

Pull Request - State: closed - Opened by shu65 about 4 years ago - 6 comments
Labels: enhancement

#54 - [DO NOT MERGE] Update README.md

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

#53 - Apply isort in CI

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

#52 - [DO NOT MERGE] Update README.md

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

#51 - how to deal output of GaussianHeadWithStateIndependentCovariance

Issue - State: closed - Opened by kakuriyama about 4 years ago - 6 comments

#50 - Implement optimize_hooks in agents

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

#49 - Adds more examples to documentation

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

#48 - Saving training statistics

Issue - State: closed - Opened by tkelestemur about 4 years ago - 2 comments

#47 - Added Option Critic Network Builder

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

#46 - Optuna integration & example script (2)

Pull Request - State: closed - Opened by keisuke-nakata over 4 years ago - 12 comments
Labels: enhancement, example

#45 - [WIP] - DON'T Review - Add HRL Agent + HIRO

Pull Request - State: closed - Opened by peasant98 over 4 years ago

#44 - Tuples are not unpacked when using 'unpack_sequences_as_one_step_batch'

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

#43 - Enable auto assignment of PR reviewers

Pull Request - State: closed - Opened by muupan over 4 years ago
Labels: testing

#42 - [Do Not Merge] Update README.md

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

#41 - Indicate that recurrent is not supported by DDPG

Pull Request - State: closed - Opened by muupan over 4 years ago
Labels: documentation

#40 - Error when using no_grad () and lazy_property

Issue - State: closed - Opened by shu65 over 4 years ago
Labels: bug

#39 - Adjusts the logo to fix aspect ratio

Pull Request - State: closed - Opened by prabhatnagarajan over 4 years ago - 2 comments
Labels: documentation

#38 - Recurrent DDPG implemented?

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

#37 - Link Rainbow paper in training scripts

Pull Request - State: closed - Opened by marioyc over 4 years ago - 2 comments
Labels: documentation

#36 - [Fix Examples] function call was duplicated

Pull Request - State: closed - Opened by gorogoroyasu over 4 years ago - 2 comments
Labels: example

#35 - Add PFRL Logo to Readme

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

#34 - Adds PFRL logo to assets

Pull Request - State: closed - Opened by prabhatnagarajan over 4 years ago - 2 comments
Labels: documentation

#33 - Pretrained models

Pull Request - State: closed - Opened by prabhatnagarajan over 4 years ago - 21 comments
Labels: enhancement, example

#32 - calculate scalar q_values to log average_q statistics in categorical dqn algorithms

Pull Request - State: closed - Opened by keisuke-nakata over 4 years ago
Labels: bug

#30 - Make update_counter multiprocess safe

Pull Request - State: closed - Opened by belldandyxtq over 4 years ago - 4 comments
Labels: bug

#29 - [WIP] Pretrained models

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

#28 - [WIP] Adds Pretrained Models

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

#27 - Remove variables previously used for backward compatibility

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

#26 - tests/agents_tests/test_double_dqn.py with gpu is flaky

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

#25 - IQN Benchmark results

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

#24 - Rainbow benchmark results

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

#23 - DQN benchmark results

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

#22 - Replace GIFs to reflect PFRL results

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

#21 - Optuna integration & example script

Pull Request - State: closed - Opened by keisuke-nakata over 4 years ago - 35 comments

#20 - Updates A3C results with PFRL results

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

#19 - Improve quickstart guide

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

#18 - Update self._cumulative_steps in non-actor-learner training

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

#17 - Add type hints to DQN and its dependencies

Pull Request - State: closed - Opened by muupan over 4 years ago - 1 comment
Labels: enhancement

#16 - Add type hints to agent interfaces

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

#15 - Remove unused --use-sdl

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

#14 - Add a Slime Volleyball example

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

#13 - Remove `sample_with_log_prob` and use `cache_size=1` instead

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

#12 - Adds optional logging of evaluator to tensorboard

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

#11 - Fix wrong event shape handling in sample_with_log_prob

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

#10 - ExponentialDecayEpsilonGreedy

Pull Request - State: closed - Opened by keisuke-nakata over 4 years ago - 9 comments

#9 - remove `gpus` argument from set_random_seed

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

#8 - Fix A3C dtype error with torch>=1.5.0

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

#7 - Update SAC results

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

#6 - Hindsight Experience Replay

Issue - State: open - Opened by prabhatnagarajan over 4 years ago - 5 comments

#5 - Test quickstart in CI

Pull Request - State: closed - Opened by muupan over 4 years ago - 7 comments

#4 - Double IQN

Issue - State: open - Opened by prabhatnagarajan over 4 years ago - 3 comments

#3 - Add Atari benchmark scores

Issue - State: closed - Opened by prabhatnagarajan over 4 years ago

#2 - Add Pretrained Models

Issue - State: closed - Opened by prabhatnagarajan over 4 years ago