-
Hi,
I could not finish tests, even though it took over 3 hours. Could you tell me what is my bad?
It seems that `test_pcl.TestPCL.test_abc_discrete` is stacking. My guess is `steps` for `_test…
-
1) The training law of the Actor network (Eq.2) uses the gradient of the network times the reward difference A, to evolve the model of the neural network
Is the term "detla_theda log pi_theda (s_t,…
-
Hi @ebonyclock , I wanna train an agent in health_grathering scenario with A3C algorithm, to train it
`python3 train_a3c.py -s settings/health_gathering.yml`
with `a3c_defaults.yml` settings.
…
-
How many days/episodes did it take until it converged in breakout_a3c? Did you try using LSTM for faster convergence?
-
Batch normalization layer ([paper](https://arxiv.org/pdf/1502.03167.pdf)) is widely used when training deep networks. It appears that batch normalization make the network learning faster and generaliz…
-
I wonder why `os.environ['OMP_NUM_THREADS'] = '1'` is used in the `main` method: https://github.com/ikostrikov/pytorch-a3c/blob/master/main.py#L43.
I ran a demo about CartPole-v0 using openai gym w…
-
Hi @Kaixhin
I wonder if the sigma in NoisyNet-A3C will fast shrink to nearly zero or not.
since if the values of the sigma is nearly zero, no exploration will be done by the agent.
The reason why …
-
Hi, Pong is a good sanity check. Has anyone tried/adopted the code (A3C-LSTM) on other Atari games like BreakoutDeterministic-v3 and SpaceInvadersDeterministic-v3, and managed to get average scores 50…
-
Hi @miyosuda ,
Thank you for sharing the code.
When I tried to run the code, I came across some problem.
'''
Traceback (most recent call last):
File "a3c.py", line 50, in
global_network =…
-
Training Breakout goes ok but, memory usage exceeds 25gb after 4 hours of training on 16 cpu cores.
I wonder if it's related to sharing memory between processes.
I run Python 3.5 on scientific lin…