jerrodparker20 adaptive-transformers-in-rl issues - Githubissues

jerrodparker20 / adaptive-transformers-in-rl

Adaptive Attention Span for Reinforcement Learning

130 stars 14 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Error reproducing results

#19 doltonfernandes opened 2 years ago
0
Isn't param "--use_gate" important for Pong?

#18 weihongwei0586 opened 3 years ago
0
Regarding logic for first done indexes

#17 victor-psiori opened 3 years ago
1
Stable Transformer on Pong

#16 furmans opened 3 years ago
2
Is this algorithm suitable for off-policy policy?

#15 dbsxdbsx opened 3 years ago
1
Could you share a pre-trained model of 'Pong' ?

#14 alimai opened 3 years ago
0
Get Steps 0 @ 0.0 SPS. Loss inf. Stats

#13 ghost closed 3 years ago
8
train.py on colab, using snippets

#12 yhg8423 closed 4 years ago
4
Gcp debug

#11 shaktikshri closed 4 years ago
0
Gcp debug adaptive

#10 shaktikshri closed 4 years ago
0
Gcp debug adaptive

#9 shaktikshri closed 4 years ago
0
Gcp debug

#8 shaktikshri closed 4 years ago
0
Gcp debug adaptive

#7 shaktikshri closed 4 years ago
0
Gcp debug

#6 shaktikshri closed 4 years ago
0
Reordered initialization of last_n_episode returns (was defined after…

#5 shaktikshri closed 4 years ago
0
Gcp debug

#4 shaktikshri closed 4 years ago
0
Dmlab30

#3 shaktikshri closed 4 years ago
0
Dynamic batching

#2 shaktikshri closed 4 years ago
0
Find bug

#1 shaktikshri closed 4 years ago
0