google-research seed_rl issues

google-research / seed_rl

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

Apache License 2.0

798 stars 146 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Security Policy violation Binary Artifacts

#83 google-allstar-prod[bot] closed 1 year ago
22
Fix GPG error due to NVIDIA updates on repository signing keys

#82 qzweng closed 1 year ago
0
KL loss implementation is less effective

#81 YuriCat closed 1 year ago
0
Trouble reproducing reported training FPS

#80 mx781 closed 1 year ago
1
Language

#79 CZtheHusky closed 2 years ago
1
Missing learning curve data for `Defender` `Surround`

#78 vwxyzjn closed 1 year ago
7
Using tensorflow grpc causes memory leaks when calling to server

#77 YHL04 closed 1 year ago
1
num_action_repeats=1 flag correct for Atari?

#76 holger-m closed 1 year ago
2
Need some help about applying IMPALA to Atari game

#75 kimbring2 closed 2 years ago
1
Looking for v-mpo configs/examples

#74 Denys88 closed 1 year ago
0
Looking for clarification on entropy loss calculations for vtrace agent

#73 Edvard-D closed 1 year ago
0
Strange loss values from vtrace agent

#72 Edvard-D closed 1 year ago
0
Update is needed to Dockerfile.dmlab file

#71 kimbring2 closed 3 years ago
1
Does SEED ensure that there doesn't end up being a backlog of inferences in the unroll queue?

#70 Edvard-D closed 3 years ago
1
Impossible to run SEED using TPUs with Google Cloud AI Platform

#69 Edvard-D closed 3 years ago
1
"Permission denied" error while running /docker/build.sh

#68 Edvard-D closed 3 years ago
1
Multi-agents support

#67 THULiusj closed 1 year ago
0
A temporal fix for RTX30s graphics card and cuda11 dependencies

#66 VegeWong closed 1 year ago
2
PPO agent event logging could stuck

#65 sdumpling closed 1 year ago
0
ERROR: An error occurred during the fetch of repository 'jpeg_archive'

#64 Pranav-India closed 3 years ago
3
TF 2.4.1 and gRPC

#63 ideenfix closed 3 years ago
4
Is the gcp/train_atari.sh script actually using one GPU device for training?

#62 bingykang closed 3 years ago
1
What is the use case for the tensorflow gRPC batched functions?

#61 trouverun closed 3 years ago
2
R2D2 - Why is the time index t+1 for replay_q?

#60 Near32 closed 1 year ago
0
Why "dones" need zero padding in stack_frames of R2D2?

#59 sorryformyself closed 3 years ago
2
Problem of Running distributed version

#58 Maxwell2017 closed 1 year ago
8
Is there a testing mode in seed-rl?

#57 Olin1461 closed 3 years ago
2
The reason for clipped reward in V-trace

#56 benlin1996 closed 3 years ago
2
how to analyse my GPU memory usage details

#55 giantvision closed 3 years ago
3
Re-initialize agent in the middle of learner

#54 benlin1996 closed 3 years ago
4
Which approach to the on-policy training/inference synchronization is best?

#53 Antymon closed 3 years ago
2
Unable to update non-tensor variable in the tf.function

#52 benlin1996 closed 3 years ago
4
Unable to reproduce Pong results with a local single-GPU run and paper hyper-params

#51 Antymon closed 1 year ago
6
How to load a saved_model.pb file and continue training on it?

#50 Moradnejad closed 3 years ago
2
Grpc is incompatible with tf2 if tf2 was built from source

#49 treeeeke closed 1 year ago
8
Training on Standalone Machine Fails

#48 mosicr closed 4 years ago
0
Definition of batched changed ?

#47 jrabary closed 3 years ago
1
ImportError: libGL.so.1 while running locally

#46 suwangcompling closed 4 years ago
0
Running Seed RL on TPU

#45 mosicr closed 4 years ago
2
'GrpcServerResourceHandleOp' is neither a type of a primitive operation nor a name of a function registered in binary running on n-b0fdb3cc-w-0.

#44 brieyla1 closed 1 year ago
17
Cannot assign a device for operation Aggregator/Gather

#43 brieyla1 closed 4 years ago
3
Unable to Instantiate gRPC Server

#42 hyang0129 closed 4 years ago
4
Loading and running trained models

#41 sharsnik2 closed 4 years ago
9
Can this be used with non-image Gym environments?

#40 hai-h-nguyen closed 4 years ago
1
About sac_main.y

#39 BlackDeal closed 1 year ago
1
How to run sac?

#38 BlackDeal closed 4 years ago
1
switch 'time' dimension and 'stack' dimension on/off for R2D2 during training/inference

#37 turmeric-blend closed 4 years ago
1
how to detach replay buffer from GPU memory during training and inference

#36 turmeric-blend closed 4 years ago
1
Dockerfile examples for custom env?

#35 sophiagu closed 4 years ago
0
no server running on /tmp/tmux-0/default

#34 vrindger closed 4 years ago
1