google-deepmind bsuite issues

google-deepmind / bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

Apache License 2.0

1.51k stars 182 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

`bsuite` using `np.int` which is deprecated.

#53 marcdelabarrera opened 5 months ago
0
Incompatible with Python 3.12

#52 pseudo-rnd-thoughts opened 6 months ago
2
Replace imp with importlib for Python 3.12 support

#51 cool-RR opened 7 months ago
1
Replace imp with importlib

#50 fabaff opened 7 months ago
0
Fix getattr

#49 jjshoots opened 1 year ago
1
Convert `np.int -> np.int32` since `np.int` is deprecated

#48 jjshoots opened 1 year ago
1
Incompatible with numpy>0.24

#47 epignatelli opened 1 year ago
0
Tensorflow BOOT DQN agent loses performance after first iteration

#46 anyboby opened 1 year ago
0
How to add the results to results.py? What's the results format should be?

#45 yvxxyh closed 1 year ago
1
Deprecate `Catch._observation` for `Catch.get_observation`

#44 epignatelli opened 1 year ago
0
`Catch._observation` does not follow the other environments with `_get_observation`

#43 epignatelli opened 1 year ago
0
_total_steps assignment position bug

#42 MichelangeloConserva opened 2 years ago
0
Update setup.py

#41 anukaal opened 3 years ago
0
Fix radar plot error

#40 ethanabrooks opened 3 years ago
0
Cartpole environment observation parameters

#39 kbkartik closed 3 years ago
1
MDP Playground integration into bsuite

#38 RaghuSpaceRajan opened 3 years ago
5
BootDQN+ not matching claimed performance

#37 bycn closed 3 years ago
17
Environment seeding

#36 adamxyang closed 3 years ago
1
Expose render method for DMEnvFromGym

#35 epignatelli closed 1 year ago
0
The signature for `update` does not allow for sarsa or n-step methods?

#34 epignatelli closed 3 years ago
1
inconsistency fix for stochastic deep sea

#33 cgao3 opened 4 years ago
2
Default number of ensemble

#32 AlexPiche opened 4 years ago
2
Documentation: Clarify mapping from high-level agent properties to experiments and environments

#31 aaronsnoswell opened 4 years ago
2
Updating docs on loading up data

#30 DavidJanz closed 4 years ago
1
threadlimit

#29 DavidJanz closed 1 year ago
8
add 'loading_message' flag to env loaders

#28 bionicles opened 4 years ago
2
Import ABC from collections.abc

#27 tirkarthi opened 4 years ago
2
Importing ABC directly from collections will be removed in Python 3.10

#26 tirkarthi closed 3 years ago
2
Using the agent's RNG, and not numpy's, to select actions

#25 RaghuSpaceRajan closed 4 years ago
1
Fix bsuite datasets.py reshape bug.

#24 mikebjohanson closed 4 years ago
1
Question about DQN's loss

#23 toshikwa closed 4 years ago
1
dependency on trfl breaks TF2

#22 filangelos closed 4 years ago
2
setup.py broken after last commit

#21 MichelangeloConserva closed 4 years ago
2
DQN mnist & mountain car performance

#20 pluebcke opened 4 years ago
16
How is the 'generalization' score computed?

#19 VincentLiu3 closed 4 years ago
1
bsuite_tutorial problem when build PPO OpenAI baseline agent

#18 lingjunz closed 4 years ago
1
Cannot import Random

#17 JaroslavVitku closed 4 years ago
2
Rendering control environments

#16 neale closed 4 years ago
2
environment/experiment with continuous action space, Box()

#15 junhuang-ifast closed 5 years ago
1
Can't reproduce DQN performance

#14 SunCherry closed 5 years ago
2
In deep_sea the threshold is set to 0.8 instead of 0.9 as the paper indicates.

#13 lcassano closed 5 years ago
0
Westworld host attribute matrix

#12 viliwonka closed 5 years ago
1
bsuite_tutorial.ipynb error - load bsuite environments as OpenAI gym-

#11 SoyGema closed 5 years ago
4
bsuite uninstalls tensorflow-gpu==2.0.0-rc1 when installing baselines via cloned repo

#10 bionicles closed 5 years ago
1
Adding a pendulum environment/experiment

#9 alexminnaar closed 5 years ago
1
adding reverse openai gym wrapper and tests

#8 alexminnaar closed 5 years ago
5
Reverse gym wrapper

#7 alexminnaar closed 5 years ago
2
Converting Openai gym environments to bsuite environments

#6 alexminnaar closed 5 years ago
2
Merge pull request #1 from deepmind/master

#5 alexminnaar closed 5 years ago
0
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?

#4 MatPoliquin closed 5 years ago
1