dacbench.envs.policies.sgd_ca
Module Contents
Classes
Abstract class to implement for use with the runner function |
- class dacbench.envs.policies.sgd_ca.CosineAnnealingAgent(env, base_lr=0.1, t_max=1000, eta_min=0)
Bases:
dacbench.abstract_agent.AbstractDACBenchAgentAbstract class to implement for use with the runner function
- act(self, state, reward)
Compute and return environment action
- Parameters
state – Environment state
reward – Environment reward
- Returns
Action to take
- Return type
action
- train(self, state, reward)
Train during episode if needed (pass if not)
- Parameters
next_state – Environment state after step
reward – Environment reward
- end_episode(self, state, reward)
End of episode training if needed (pass if not)
- Parameters
state – Environment state
reward – Environment reward