-
As far as I can see, model hyperparameters are different.
Thanks.
-
I want to use a TensorGraph GRU layer as part of a model for reinforcement learning. It's not clear how to make that work. I'm pretty sure it's going to need some modifications, but I'm not certain …
-
Would it be possible to provide examples for stateful models for q learning and a3c?
-
[Layer normalization](https://arxiv.org/abs/1607.06450) seems to be pretty popular for RNNs nowadays, and it is worth having an implementation available. Several people seem to have already rolled the…
-
Hello :)
I was wondering how to modify the code for continuous actions? So for example it could be compared with your naf implementation on openAI gym pendulum,
`env = gym.envs.make("Pendulum-v0…
-
Dear Juliani
Excellent work!
I would like to know for how long you trained the A3C? and Number of frames used?
How do you find your your results compared to the original paper? (Denny code …
-
https://github.com/ikostrikov/pytorch-a3c has an implementation (CPU ONLY) that can converge PongDeterministic-v3 within 15 minutes while the GPU powered GA3C appears to take 2-3 hours to achieve the …
-
Setting up openai/universe, I used the "universe starter agent" as a smoke test.
After adjusting the number of workers to better utilize my CPU, I saw the default PongDeterministic-v3 start winnin…
-
I've been playing around with the example code for a few days now but I keep getting the same issue:
eg for Pong, after about 3 hours of training, the TensorBoard global/episode_reward goes to about …
-
I should support A3C LSTM.