In the dqn_agent.py the used tf.keras.layers.Dense(TF2.0) does not support graph reuse as in the way it is intended to. Hence N number of graphs are being initialised.
using tf.layers.dense, inplace of tf.keras.layers.Dense was able to overcome the issue for now.
Sandy4321
commented
9 months ago
In the dqn_agent.py the used tf.keras.layers.Dense(TF2.0) does not support graph reuse as in the way it is intended to. Hence N number of graphs are being initialised.
using tf.layers.dense, inplace of tf.keras.layers.Dense was able to overcome the issue for now.