Dreamer V3 on custom environment

1

Hi all,
I am trying to implement dreamer v3 on my custom environment with
action_space = gym.spaces.Box(low=-np.inf, high=np.inf, shape=(64,), dtype=np.float32)
observation_space = gym.spaces.Box(low=-np.inf, high=np.inf, shape=(204,), dtype=np.float32)

The following errors were raised
AttributeError: Exception encountered when calling layer ‘dreamer_model’
AttributeError: Exception encountered when calling layer ‘dynamics_predictor’
AttributeError: Exception encountered when calling layer ‘z32x32’
Call arguments received by layer ‘dreamer_model’ (type DreamerModel):
• inputs=None
• observations=tf.Tensor(shape=(1, 64, 204), dtype=float32)
• actions=tf.Tensor(shape=(1, 64, 64), dtype=float32)
• is_first=tf.Tensor(shape=(1, 64), dtype=bool)
• start_is_terminated_BxT=tf.Tensor(shape=(64,), dtype=bool)

Not too sure whether this might be because of my differ obs and action space instead of the standard 64,64,3, I have tried to use the dreamer catalogclass but it is still not working, any ideas?

many thanks

2

pip install tensorflow-probability

and then run your script again

3

Thank you very much for your response
My code is working now, but for some reason, tensorflow is not using my GPU at all, I installed tf with GPU using pip

print(tf.config.list_physical_devices(‘GPU’))
returns [PhysicalDevice(name=‘/physical_device:GPU:0’, device_type=‘GPU’)]

I also set num_gpu=1 in ray.init
and have set .resources(num_gpus=int(os.environ.get(“RLLIB_NUM_GPUS”, “1”))) to my config

when I run the code, ray does say GPU 0/1.0, but the code is simply not using it at all,
any ideas why? thank you

5

Sorry for bothering you again
when I call config.build(), the problem recurs,
but it’s fine if I call tune.Tuner(trainable=“DreamerV3”,
param_space=config)

Do you have any idea why?
I want to define a train function with config.build() so that I can pass it to tune_with_resources, thanks