Skip to content
This repository has been archived by the owner on Dec 11, 2022. It is now read-only.

Issues: IntelLabs/coach

Clear current search query, filters, and sorts
73 Open 142 Closed
73 Open 142 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

AtariInputFilter is missing cropping to 84x84 after rescaling to 110x84 priority/p2 questions needing answered or medium impact bugs
#186 opened Jan 9, 2019 by gal-leibovich
IMPALA implementation enhancement priority/p1 broken basics or large value add enhancements (highest priority)
#213 opened Jan 31, 2019 by scttl
[How-to] Learning by Playing – Solving Sparse Reward Tasks from Scratch question
#222 opened Feb 18, 2019 by redknightlois
Coach docker image with Python3.6 enhancement
#236 opened Mar 3, 2019 by mattiasmar
When resuming from a checkpoint, the naming should continue from there.
#248 opened Mar 13, 2019 by redknightlois
Test Mujoco 2.0 with current presets
#266 opened Mar 26, 2019 by gal-leibovich
Normalised Advantage Function output nan action.
#357 opened Jun 20, 2019 by BigRiceBall-zz
Out of bounds error in Categorical DQN
#363 opened Jun 28, 2019 by redknightlois
NoisyNetDense noise added to evaluations
#368 opened Jul 5, 2019 by redknightlois
Ranking Policy Gradient
#380 opened Jul 22, 2019 by redknightlois
Transition is NoneType in PER when using Rainbow
#388 opened Aug 8, 2019 by hughesmc
ERROR installing rl_coach - It worked one week ago
#389 opened Aug 13, 2019 by Eriz11
Stuck after 400 episodes
#395 opened Aug 30, 2019 by DiegoBastosCosta
Implementation detail in QRDQN
#397 opened Sep 4, 2019 by Officium
Model Zoo
#406 opened Sep 23, 2019 by Amin-Tgz
CompoundActionSpace contains() call always fails
#420 opened Oct 23, 2019 by dans-msft
Odd DQN agent behavior with simple custom env
#433 opened Jan 10, 2020 by LukasMadzik
assisted learning
#436 opened Jan 17, 2020 by jingrui-who
Coach vs RLLib's Trainable and Tune hyperparam search
#439 opened Mar 24, 2020 by drozzy
Integration with wandb?
#441 opened Mar 24, 2020 by drozzy
Problem adding a driving benchmark to an experimental suit in CARLA_DDPG
#443 opened Apr 20, 2020 by Jidenna
Simple Behavioral Cloning example
#445 opened May 8, 2020 by meteoiker
What would be the best way to use a pre-trained autoencoder as an image input embedder?
#446 opened May 19, 2020 by Kurtoid
Deploying distributed learning on University cluster
#455 opened Jul 8, 2020 by mohammad200h
How to use UCB Exploration via Q-Ensembles
#457 opened Jul 21, 2020 by chelseas
ProTip! Add no:assignee to see everything that’s not assigned.