Ben Arnao
Ben Arnao
``` RainbowAgent(sess=tensorflow.compat.v1.Session(), num_actions=2, stack_size=4, observation_shape=samples[0].shape, observation_dtype=tensorflow.float32) ``` I get error ``` ValueError: Dimension 0 in both shapes must be equal, but are 32 and 3232. Shapes are [32] and [3232]....
In a few different scenarios you'd want to have nested parameters, but sometimes a parameter isn't just a numerical/string value but instead a layer or object. An obvious example would...
Is there a good way to make # of layers a parameter? I noticed if i do something like the following ``` def build_fn(input_shape): model = Sequential([ Dense(Integer(50, 150), input_shape=input_shape,...
Obviously very problem dependent as usual, but for the noise of the perturbations this is set to the 0.02 standard dev in the config (also in the paper apparently we...
**Describe the feature and the current behavior/state.** It has been shown that decoupling weight decay from the learning rate can simply hyper parameter search and leads to better performance. https://arxiv.org/abs/1711.05101...
beta1_power = math_ops.cast(self._get_non_slot_variable("beta1_power", graph=graph), var.dtype.base_dtype) No configuration changes on my end, throwing an error that beta power1 is None.
I'm getting this error even when i've parsed the exchangeInfo api and trimmed my price value to the appropriate asset precision. It's also above the minPrice value as well. Can't...
- Remove unused params from HP values dict - Find a way to prevent users from defining a param outside of conf build function (done) - Auto sort ordered params...