Open steffencruz opened 1 year ago
In the neuron source code there is a backward call to the dendrite pool
# Pass rewards backward for potential PPO. if train_network: self.dendrite_pool.backward( forward_calls = forward_calls, rewards = rewards, timeout = timeout ) bittensor.logging.trace( 'Applied backward to network.' )
What is this doing and how can we include this? @joeylegere
Make use of fitness values in DummyDendritePool #68 and adjust uid-specific fitness based on rewards in the backward call
fitness
@joeylegere Interesting question is: "Does backprop into the network have a beneficial effect on the network or just the validator?"
This requires some thought and we're not convinced that it's valuable to us.
In the neuron source code there is a backward call to the dendrite pool
What is this doing and how can we include this? @joeylegere
Possible solution
Make use of
fitness
values in DummyDendritePool #68 and adjust uid-specific fitness based on rewards in the backward call