google-deepmind/bsuite issues and pull requests

#53 - `bsuite` using `np.int` which is deprecated.

Issue - State: open - Opened by marcdelabarrera 5 months ago

#52 - Incompatible with Python 3.12

Issue - State: open - Opened by pseudo-rnd-thoughts 6 months ago - 2 comments

#51 - Replace imp with importlib for Python 3.12 support

Pull Request - State: open - Opened by cool-RR 8 months ago - 1 comment

#50 - Replace imp with importlib

Pull Request - State: open - Opened by fabaff 8 months ago

#49 - Fix getattr

Pull Request - State: open - Opened by jjshoots over 1 year ago - 1 comment

#48 - Convert `np.int -> np.int32` since `np.int` is deprecated

Pull Request - State: open - Opened by jjshoots over 1 year ago - 1 comment

#47 - Incompatible with numpy>0.24

Issue - State: open - Opened by epignatelli almost 2 years ago

#46 - Tensorflow BOOT DQN agent loses performance after first iteration

Issue - State: open - Opened by anyboby almost 2 years ago

#45 - How to add the results to results.py? What's the results format should be?

Issue - State: closed - Opened by yvxxyh almost 2 years ago - 1 comment

#44 - Deprecate `Catch._observation` for `Catch.get_observation`

Pull Request - State: open - Opened by epignatelli almost 2 years ago

#43 - `Catch._observation` does not follow the other environments with `_get_observation`

Issue - State: open - Opened by epignatelli almost 2 years ago

#42 - _total_steps assignment position bug

Pull Request - State: open - Opened by MichelangeloConserva about 2 years ago

#41 - Update setup.py

Pull Request - State: open - Opened by anukaal about 3 years ago
Labels: cla: yes

#40 - Fix radar plot error

Pull Request - State: open - Opened by ethanabrooks over 3 years ago
Labels: cla: yes

#39 - Cartpole environment observation parameters

Issue - State: closed - Opened by kbkartik over 3 years ago - 1 comment

#38 - MDP Playground integration into bsuite

Pull Request - State: open - Opened by RaghuSpaceRajan over 3 years ago - 5 comments
Labels: cla: yes

#37 - BootDQN+ not matching claimed performance

Issue - State: closed - Opened by bycn almost 4 years ago - 17 comments

#36 - Environment seeding

Issue - State: closed - Opened by adamxyang almost 4 years ago - 1 comment

#35 - Expose render method for DMEnvFromGym

Pull Request - State: closed - Opened by epignatelli almost 4 years ago
Labels: cla: no

#34 - The signature for `update` does not allow for sarsa or n-step methods?

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

#33 - inconsistency fix for stochastic deep sea

Pull Request - State: open - Opened by cgao3 about 4 years ago - 2 comments
Labels: cla: yes

#32 - Default number of ensemble

Pull Request - State: open - Opened by AlexPiche about 4 years ago - 2 comments
Labels: cla: yes

#31 - Documentation: Clarify mapping from high-level agent properties to experiments and environments

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

#30 - Updating docs on loading up data

Pull Request - State: closed - Opened by DavidJanz over 4 years ago - 1 comment
Labels: cla: yes

#29 - threadlimit

Pull Request - State: closed - Opened by DavidJanz over 4 years ago - 8 comments
Labels: cla: yes

#28 - add 'loading_message' flag to env loaders

Pull Request - State: open - Opened by bionicles over 4 years ago - 2 comments

#27 - Import ABC from collections.abc

Pull Request - State: open - Opened by tirkarthi over 4 years ago - 2 comments
Labels: cla: yes

#26 - Importing ABC directly from collections will be removed in Python 3.10

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

#25 - Using the agent's RNG, and not numpy's, to select actions

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

#24 - Fix bsuite datasets.py reshape bug.

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

#23 - Question about DQN's loss

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

#22 - dependency on trfl breaks TF2

Issue - State: closed - Opened by filangelos over 4 years ago - 2 comments
Labels: bug

#21 - setup.py broken after last commit

Issue - State: closed - Opened by MichelangeloConserva over 4 years ago - 2 comments
Labels: bug

#20 - DQN mnist & mountain car performance

Issue - State: open - Opened by pluebcke over 4 years ago - 16 comments
Labels: baselines

#19 - How is the 'generalization' score computed?

Issue - State: closed - Opened by VincentLiu3 over 4 years ago - 1 comment

#18 - bsuite_tutorial problem when build PPO OpenAI baseline agent

Issue - State: closed - Opened by lingjunz almost 5 years ago - 1 comment

#17 - Cannot import Random

Issue - State: closed - Opened by JaroslavVitku almost 5 years ago - 2 comments

#16 - Rendering control environments

Issue - State: closed - Opened by neale about 5 years ago - 2 comments
Labels: enhancement

#15 - environment/experiment with continuous action space, Box()

Issue - State: closed - Opened by junhuang-ifast about 5 years ago - 1 comment

#14 - Can't reproduce DQN performance

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

#13 - In deep_sea the threshold is set to 0.8 instead of 0.9 as the paper indicates.

Issue - State: closed - Opened by lcassano about 5 years ago

#12 - Westworld host attribute matrix

Issue - State: closed - Opened by viliwonka about 5 years ago - 1 comment

#11 - bsuite_tutorial.ipynb error - load bsuite environments as OpenAI gym-

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

#10 - bsuite uninstalls tensorflow-gpu==2.0.0-rc1 when installing baselines via cloned repo

Issue - State: closed - Opened by bionicles about 5 years ago - 1 comment

#9 - Adding a pendulum environment/experiment

Issue - State: closed - Opened by alexminnaar about 5 years ago - 1 comment

#8 - adding reverse openai gym wrapper and tests

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

#7 - Reverse gym wrapper

Pull Request - State: closed - Opened by alexminnaar about 5 years ago - 2 comments

#6 - Converting Openai gym environments to bsuite environments

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

#5 - Merge pull request #1 from deepmind/master

Pull Request - State: closed - Opened by alexminnaar about 5 years ago

#4 - ValueError: Variable ppo2_model/pi/mlp_fc0/w/Adam/ already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope?

Issue - State: closed - Opened by MatPoliquin over 5 years ago - 1 comment

#3 - changing relative urls to absolute urls in README

Pull Request - State: closed - Opened by alexminnaar over 5 years ago - 1 comment

#2 - Update results.ipynb

Pull Request - State: closed - Opened by yasuiniko over 5 years ago - 5 comments

#1 - dm_env: Broken Link

Issue - State: closed - Opened by filangelos over 5 years ago - 2 comments

GitHub / google-deepmind/bsuite issues and pull requests