async-rl
async-rl copied to clipboard
coreylynch
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
Whenever I try to start the training I get the error: `FailedPreconditionError (see above for traceback): Attempting to use uninitialized value conv2d_1/kernel`
I guess this code is written in old tensorflow? ``` x = tf.reshape(x, tf.pack([-1, prod(shape(x)[1:])])) AttributeError: 'module' object has no attribute 'pack' ``` Is it possible that this code updated...
Has anyone else had this problem when running the example code?
How to use the raw RGB instead of the grayscaled image ? I have some troubles with the neural networks shape which doesn't match the observation shape (84,84,3) ?
I'm interested as to why you decided not to create a local copy of the variables in the worker threads and sync them with the global network at the end...
I ran the async dqn model out of the box with 3 seeds on 7 atari games on 24 threads -- Pong, Breakout, SeaQuest, BeamRider, SpaceInvaders, Qbert, and Enduro. However,...
Excuse me, as I execute your program, I've got an error in tensorflow initialize： Attempting to use uninitialized value convolution2d_1_W [[Node: convolution2d_1_W/read = Identity[T=DT_FLOAT, _class=["loc:@convolution2d_1_W"], _device="/job:localhost/replica:0/task:0/cpu:0"](convolution2d_1_W)]] How can I slove...
Metadata
Owner
Metadata
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"