-
Hi,
Will the benchmark code of four navigation algorithms in the paper be released?
Also, how long does it take to train the agents? My english is poor, so I have some confusion about the followin…
-
It is a great work. Is there any plan to develop a LSTM version?
-
The depth data is not included in the data set you shared, but this error message appeared during the training process.
Training started from: 2020-09-03 10:23:59
Scene Data Exists!
initialized o…
-
hi @Kismuz
I was reading the paper "Noisy Network for exploration". And have a question w.r.t its usage in btgym. The paper says that "As A3C is an on-policy algorithm the gradients are unbiased w…
-
This thread is used for sharing experiment results. I'd appreciate if you could write your experiment result to this thread when you try my code. The following messages are sample reports.
-
@Kismuz,
I believe I have encountered a framework (A3C) limitation.
While training a few of my recent models I noticed a strange behavior. For the first part of training everything seems to work fi…
-
아래의 명령으로 실행했습니다.
python main.py --stock_code 005930 005380 015760 --rl_method a3c --net lstm --num_steps 5 --learning --num_epoches 1000 --lr 0.001 --start_epsilon 1 --discount_factor 0.9 --output_na…
-
## Description
- There is an MXNet nightly benchmark which runs CV and NLP models on MXNet Nightly pip wheel and report the metrics and it showed a performance regression on GPU Memory.
- After bise…
-
Hello @miyosuda,
Thanks for sharing the code, please ignore the title, I tried out your code with the control problem of cartpole balance experiment instead of Atari game, it works well. But few ques…
-
class M1(DQNConfig):
backend = 'tf'
env_type = 'detail'
action_repeat = 1
class M2(DQNConfig):
backend = 'tf'
env_type = 'detail'
action_repeat = 4
I use
python m…