Kaixhin Rainbow issues - Githubissues

Kaixhin / Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

MIT License

1.55k stars 281 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Data Effiecient Rainbow with Skiing does not work

#86 Somjit77 closed 1 year ago
4
Montezuma's revenge - has this been tried using this codebase?

#85 sunchipsster1 opened 1 year ago
2
Update main.py

#84 foersterrobert closed 2 years ago
0
A problem about one game in ALE cannot be trained

#83 Hugh-Cai opened 3 years ago
1
Stuck in memory._retrieve when batch size > 32

#82 jiwoongim opened 3 years ago
1
Fix IndexError caused by Numpy rounding

#81 Aladoro closed 3 years ago
2
Removed unused done variables in the main loop

#80 baballev closed 3 years ago
0
Replay buffer fix

#79 benblack769 closed 3 years ago
2
The problem about training with GPU

#78 Hugh-Cai closed 3 years ago
1
Evaluate the pretrained model

#77 Yingdong-Hu closed 3 years ago
1
IndexError: index 262141 is out of bounds for axis 0 with size 231071

#76 lucifer2859 closed 3 years ago
2
performance improvement on GPU

#75 benblack769 closed 3 years ago
1
Efficient vectorized ReplayMemory and SegmentTree

#74 Aladoro closed 3 years ago
3
Add gradient clipping

#73 Kaixhin closed 4 years ago
2
Running Rainbow on a Cluster

#72 FarhaParveen919 closed 4 years ago
1
[question] Training speed

#71 stringie closed 4 years ago
3
Explanation of Q statistics in plots for "val_mem"?

#70 andrewjmcgehee closed 4 years ago
1
load a model

#69 zyzhang1130 closed 4 years ago
1
Delayed reward

#68 zyzhang1130 closed 4 years ago
1
--learn-start

#67 zyzhang1130 closed 4 years ago
2
disable env.reset() after every episode

#66 zyzhang1130 closed 4 years ago
5
To run a demo

#65 zyzhang1130 closed 4 years ago
2
ploting the result

#64 zyzhang1130 closed 4 years ago
1
Policy and reward function

#63 zyzhang1130 closed 4 years ago
4
rainbow for multiagent setting

#62 zyzhang1130 closed 4 years ago
1
Noob Question : Need help running the code. It seems to be running for forever.

#61 YousufAzadSami closed 4 years ago
1
Infinite loop in ReplayMemory._get_sample_from_segment

#60 luisenp closed 4 years ago
1
Taking the max over step frame buffer

#59 guydav closed 4 years ago
2
Resume support

#58 guydav closed 4 years ago
14
Is the evluation procedure different?

#57 guydav opened 4 years ago
8
Hyper parameter

#56 jiafei1224 closed 4 years ago
1
Memory capacity for example data-efficient Rainbow?

#55 guydav closed 4 years ago
4
Pre-trained models param mismatch

#54 asaran closed 4 years ago
2
Building the environment with DeepMind wrappers

#53 bmazoure closed 4 years ago
1
Human-expert normalized scores

#52 ThisIsIsaac opened 4 years ago
4
Question regarding the commit : Fix stddev to match NoisyNet paper

#51 marintoro closed 4 years ago
2
properly notify & raise errors on loading pretrained models

#50 ThisIsIsaac closed 4 years ago
1
updated loading pretrained model

#49 ThisIsIsaac closed 4 years ago
3
Suggestions for improving training speed (especially when input data is large)

#48 Robotwithsoul closed 4 years ago
2
Zero-filling tensors to reset state buffer

#47 ThisIsIsaac closed 4 years ago
1
Please create documentation for --render

#46 jkterry1 closed 5 years ago
1
Non-ASCI characters used without declaring encoding

#45 jkterry1 closed 4 years ago
2
Typo in readme

#44 jkterry1 closed 5 years ago
0
Question: Where did you get the history-length concept from?

#43 albertwujj closed 5 years ago
1
Interrupted history transitions in ReplayMemory?

#42 albertwujj closed 5 years ago
4
memory file stuck in the while loop

#41 imansaj closed 5 years ago
1
Fix stddev default to match NoisyNet paper

#40 stormont closed 5 years ago
1
Fix requirements.txt: replace "pytorch" with "torch"

#39 lwneal closed 5 years ago
0
Pinned memory experience replay

#38 Kaixhin opened 5 years ago
0
float state?

#37 gorogm closed 5 years ago
1