Ecosyste.ms: Issues

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

GitHub / google-research/seed_rl issues and pull requests

#83 - Security Policy violation Binary Artifacts

Issue - State: closed - Opened by google-allstar-prod[bot] almost 2 years ago - 22 comments
Labels: allstar

#82 - Fix GPG error due to NVIDIA updates on repository signing keys

Pull Request - State: closed - Opened by qzweng about 2 years ago

#81 - KL loss implementation is less effective

Issue - State: closed - Opened by YuriCat about 2 years ago

#80 - Trouble reproducing reported training FPS

Issue - State: closed - Opened by mx781 about 2 years ago - 1 comment

#79 - Language

Pull Request - State: closed - Opened by CZtheHusky over 2 years ago - 1 comment

#78 - Missing learning curve data for `Defender` `Surround`

Issue - State: closed - Opened by vwxyzjn over 2 years ago - 7 comments

#77 - Using tensorflow grpc causes memory leaks when calling to server

Issue - State: closed - Opened by YHL04 over 2 years ago - 1 comment

#76 - num_action_repeats=1 flag correct for Atari?

Issue - State: closed - Opened by holger-m about 3 years ago - 2 comments

#75 - Need some help about applying IMPALA to Atari game

Issue - State: closed - Opened by kimbring2 about 3 years ago - 1 comment

#74 - Looking for v-mpo configs/examples

Issue - State: closed - Opened by Denys88 about 3 years ago

#72 - Strange loss values from vtrace agent

Issue - State: closed - Opened by Edvard-D over 3 years ago

#71 - Update is needed to Dockerfile.dmlab file

Issue - State: closed - Opened by kimbring2 over 3 years ago - 1 comment

#69 - Impossible to run SEED using TPUs with Google Cloud AI Platform

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

#68 - "Permission denied" error while running /docker/build.sh

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

#67 - Multi-agents support

Issue - State: closed - Opened by THULiusj over 3 years ago

#66 - A temporal fix for RTX30s graphics card and cuda11 dependencies

Pull Request - State: closed - Opened by VegeWong over 3 years ago - 2 comments
Labels: cla: no

#65 - PPO agent event logging could stuck

Issue - State: closed - Opened by sdumpling over 3 years ago

#64 - ERROR: An error occurred during the fetch of repository 'jpeg_archive'

Issue - State: closed - Opened by Pranav-India over 3 years ago - 3 comments

#63 - TF 2.4.1 and gRPC

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

#62 - Is the gcp/train_atari.sh script actually using one GPU device for training?

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

#61 - What is the use case for the tensorflow gRPC batched functions?

Issue - State: closed - Opened by trouverun almost 4 years ago - 2 comments

#60 - R2D2 - Why is the time index t+1 for replay_q?

Issue - State: closed - Opened by Near32 almost 4 years ago

#59 - Why "dones" need zero padding in stack_frames of R2D2?

Issue - State: closed - Opened by sorryformyself almost 4 years ago - 2 comments

#58 - Problem of Running distributed version

Issue - State: closed - Opened by Maxwell2017 almost 4 years ago - 8 comments

#57 - Is there a testing mode in seed-rl?

Issue - State: closed - Opened by Olin1461 almost 4 years ago - 2 comments

#56 - The reason for clipped reward in V-trace

Issue - State: closed - Opened by benlin1996 almost 4 years ago - 2 comments

#55 - how to analyse my GPU memory usage details

Issue - State: closed - Opened by giantvision almost 4 years ago - 3 comments

#54 - Re-initialize agent in the middle of learner

Issue - State: closed - Opened by benlin1996 almost 4 years ago - 4 comments

#53 - Which approach to the on-policy training/inference synchronization is best?

Issue - State: closed - Opened by Antymon almost 4 years ago - 2 comments

#52 - Unable to update non-tensor variable in the tf.function

Issue - State: closed - Opened by benlin1996 almost 4 years ago - 4 comments

#51 - Unable to reproduce Pong results with a local single-GPU run and paper hyper-params

Issue - State: closed - Opened by Antymon almost 4 years ago - 6 comments

#50 - How to load a saved_model.pb file and continue training on it?

Issue - State: closed - Opened by Moradnejad almost 4 years ago - 2 comments

#49 - Grpc is incompatible with tf2 if tf2 was built from source

Issue - State: closed - Opened by treeeeke about 4 years ago - 8 comments

#48 - Training on Standalone Machine Fails

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

#47 - Definition of batched changed ?

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

#46 - ImportError: libGL.so.1 while running locally

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

#45 - Running Seed RL on TPU

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

#43 - Cannot assign a device for operation Aggregator/Gather

Issue - State: closed - Opened by brieyla1 about 4 years ago - 3 comments

#42 - Unable to Instantiate gRPC Server

Issue - State: closed - Opened by hyang0129 over 4 years ago - 4 comments

#41 - Loading and running trained models

Issue - State: closed - Opened by sharsnik2 over 4 years ago - 9 comments

#40 - Can this be used with non-image Gym environments?

Issue - State: closed - Opened by hai-h-nguyen over 4 years ago - 1 comment

#39 - About sac_main.y

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

#38 - How to run sac?

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

#36 - how to detach replay buffer from GPU memory during training and inference

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

#35 - Dockerfile examples for custom env?

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

#34 - no server running on /tmp/tmux-0/default

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

#33 - missing grpc_cc.so file

Issue - State: closed - Opened by turmeric-blend over 4 years ago - 7 comments

#32 - How to run an agent locally

Issue - State: closed - Opened by kaustabpal over 4 years ago - 7 comments

#31 - How to decouple grpc folder for other projects?

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

#30 - ran into GRPC error when switch base docker image

Issue - State: closed - Opened by turmeric-blend over 4 years ago - 5 comments

#29 - Unity

Pull Request - State: closed - Opened by sharsnik2 over 4 years ago - 1 comment
Labels: cla: no

#27 - unexpected error when running r2d2

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

#26 - callbacks in grpc.cc

Issue - State: closed - Opened by Michaelvll over 4 years ago - 6 comments

#25 - Learning type

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

#24 - Local cluster

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

#22 - CUDA and driver requirements

Issue - State: closed - Opened by sharsnik2 over 4 years ago - 2 comments

#21 - help understanding temp_grads in learner of vtrace

Issue - State: closed - Opened by 1576012404 over 4 years ago - 1 comment

#20 - Don't have access to seed_rl bucket

Issue - State: closed - Opened by mcaleste over 4 years ago - 12 comments

#19 - run SEED_RL + R2D2 in pure inference/eval mode with one actor

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

#18 - Installation

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

#17 - Question on Vtrace Training Result Stability

Issue - State: closed - Opened by 1576012404 over 4 years ago - 1 comment

#16 - How can I train it on multi-GPU

Issue - State: closed - Opened by Da-Capo over 4 years ago - 13 comments

#15 - what is bit-packing and is it environment specific?

Issue - State: closed - Opened by turmeric-blend over 4 years ago - 8 comments

#14 - Failed to build GRPC with tf-nightly

Issue - State: closed - Opened by jrabary over 4 years ago - 11 comments

#13 - Question on R2D2 concept & implementation

Issue - State: closed - Opened by turmeric-blend over 4 years ago - 5 comments

#12 - Google research

Issue - State: closed - Opened by xmtx1 over 4 years ago - 1 comment

#11 - running R2D2 without Docker

Issue - State: closed - Opened by turmeric-blend over 4 years ago - 13 comments

#10 - grpc error on Windows 10

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

#9 - Add Num. actors parameter validation to run_local.sh

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

#8 - Remove code duplicates

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

#7 - Update football network to parametric action distribution API

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

#6 - Change number of environments

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

#5 - Problem running a GPU-based local version

Issue - State: closed - Opened by alex-petrenko almost 5 years ago

#4 - weight sync during rollout creation

Issue - State: closed - Opened by Scitator almost 5 years ago

#3 - PrioritizedReplay importance sampling weights calculation

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

#2 - Fix #1 (swapped files)

Pull Request - State: closed - Opened by CStanKonrad about 5 years ago - 2 comments
Labels: cla: yes

#1 - FIlename mismatch

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