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.
PythonApache-2.0
Issues
- 0
KL loss implementation is less effective
#81 opened by YuriCat - 22
- 1
- 7
- 1
Trouble reproducing reported training FPS
#80 opened by mx781 - 2
num_action_repeats=1 flag correct for Atari?
#76 opened by holger-m - 0
Looking for v-mpo configs/examples
#74 opened by Denys88 - 0
Strange loss values from vtrace agent
#72 opened by Edvard-D - 0
- 0
R2D2 - Why is the time index t+1 for replay_q?
#60 opened by Near32 - 0
PPO agent event logging could stuck
#65 opened by sdumpling - 0
Multi-agents support
#67 opened by THULiusj - 6
Unable to reproduce Pong results with a local single-GPU run and paper hyper-params
#51 opened by Antymon - 8
Problem of Running distributed version
#58 opened by Maxwell2017 - 17
'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 opened by brieyla1 - 8
- 7
How to run an agent locally
#32 opened by kaustabpal - 1
About sac_main.y
#39 opened by BlackDeal - 1
- 9
Loading and running trained models
#41 opened by sharsnik2 - 1
Update is needed to Dockerfile.dmlab file
#71 opened by kimbring2 - 1
Does SEED ensure that there doesn't end up being a backlog of inferences in the unroll queue?
#70 opened by Edvard-D - 1
- 2
Running Seed RL on TPU
#45 opened by mosicr - 1
- 4
TF 2.4.1 and gRPC
#63 opened by ideenfix - 1
Is the gcp/train_atari.sh script actually using one GPU device for training?
#62 opened by bingykang - 3
- 2
- 2
- 2
- 2
Is there a testing mode in seed-rl?
#57 opened by Olin1461 - 3
how to analyse my GPU memory usage details
#55 opened by giantvision - 2
The reason for clipped reward in V-trace
#56 opened by benlin1996 - 4
Re-initialize agent in the middle of learner
#54 opened by benlin1996 - 4
- 2
- 1
Definition of batched changed ?
#47 opened by jrabary - 0
Training on Standalone Machine Fails
#48 opened by mosicr - 0
- 3
- 1
how to detach replay buffer from GPU memory during training and inference
#36 opened by turmeric-blend - 1
switch 'time' dimension and 'stack' dimension on/off for R2D2 during training/inference
#37 opened by turmeric-blend - 1
- 4
Unable to Instantiate gRPC Server
#42 opened by hyang0129 - 1
How to run sac?
#38 opened by BlackDeal - 0
Dockerfile examples for custom env?
#35 opened by sophiagu - 1
no server running on /tmp/tmux-0/default
#34 opened by vrindger - 7
missing grpc_cc.so file
#33 opened by turmeric-blend - 2
How to decouple grpc folder for other projects?
#31 opened by fmxFranky