Closed jbirkesteen closed 1 year ago
When this is fixed, we should remove the definition of calculate_rewards()
from the TD-agent, so it just inherits the pass from Player()
.
When this is fixed, we should remove the definition of
calculate_rewards()
from the TD-agent, so it just inherits the pass fromPlayer()
.
TDAgent still needs to pass it, since it inherits from DirectPolicyAgent and not Player.
The way we define the
calculate_rewards()
methods inPlayer()
is actually specific to direct policy gradient methods.Therefore, the definition in
Player()
should be an empty placeholder, while the current definition is moved to the appropriateDirectPolicyAgent()
parent class.