airsplay/R2R-EnvDrop
PyTorch Code of NAACL 2019 paper "Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout"
C++MIT
Issues
- 0
Request code to generate R2R_<partition>.json
#33 opened by kaiiwoo - 3
Import MatterSim error
#32 opened by Hoyyyaard - 3
- 1
Multiple GPUs
#31 opened by wangqian621 - 1
Missing files
#30 opened by tito21 - 1
environment set up problem
#29 opened by g-jing - 2
- 2
Vanilla Listener (Follower) Training without RL (Student Forcing + Teacher Forcing?)
#27 opened by siddk - 4
Beam search validation
#26 opened by yellowjs0304 - 2
- 8
Pre-exploration in the unseen environment
#4 opened by chijames - 2
- 11
Release of pretrained snapshots
#11 opened by ayshrv - 4
- 2
How to run with multiple gpus?
#24 opened by yellowjs0304 - 1
- 2
Beam Search setting
#22 opened by HanqingWangAI - 3
One possiable bug in agent._teacher_action()
#19 opened by ZuoJiaxing - 2
- 0
Can this repo reproduce the reported result ?
#18 opened by convnets - 4
- 2
Test Question
#16 opened by xiran2018 - 4
Help, error about the code
#15 opened by xiran2018 - 2
Some issues
#12 opened by billhhh - 6
Hardware requirements?
#6 opened by daqingliu - 1
Questions about Enhanced Speaker
#9 opened by ZhuFengdaaa - 0
Submitted to VLN test server
#10 opened by Lambert-hpx - 1
How can I get the results from the paper?
#8 opened by choice37 - 2
About angle feature size
#7 opened by HanqingWangAI - 4
reward quantification
#3 opened by chijames - 2
Aligning in speaker
#5 opened by zwx8981 - 1
Paper Question
#2 opened by AmingWu - 2
appropriate argument setting?
#1 opened by zwx8981