gsnn.gsnn.optim.REINFORCE

Classes

REINFORCE(*args, **kwargs)

class gsnn.gsnn.optim.REINFORCE.REINFORCE(*args: Any, **kwargs: Any)[source]

Bases: Module

get_edge_probs()[source]

get_reward_params()[source]

print_progress_()[source]

prob_of(action)[source]

sample()[source]

scale(rewards)[source]

step()[source]

update(rewards, actions=None)[source]