junhyukoh self-imitation-learning issues - Githubissues

junhyukoh / self-imitation-learning

ICML 2018 Self-Imitation Learning

MIT License

274 stars 41 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

How the policy and the value function use the same parameters $\theta$ ?

#8 xiaobanni closed 3 years ago
1
Calculating returns with signed rewards

#7 backpropper opened 4 years ago
2
entropy in SIL policy loss

#6 gabrieledcjr opened 5 years ago
0
Policy 'lstm' doesn't work

#5 HaozhengLi opened 5 years ago
1
Key-Door-Treasure

#4 anagorko opened 5 years ago
0
SIL Value update

#3 boscotsang closed 5 years ago
2
np.sign(rewards)

#2 bhairavmehta95 closed 5 years ago
2
Missing imports: os, pandas, uuid

#1 cclauss closed 6 years ago
0