spinup/algos/pytorch/td3/td3.py [326:353]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if (t+1) % steps_per_epoch == 0:
            epoch = (t+1) // steps_per_epoch

            # Save model
            if (epoch % save_freq == 0) or (epoch == epochs):
                logger.save_state({'env': env}, None)

            # Test the performance of the deterministic version of the agent.
            test_agent()

            # Log info about epoch
            logger.log_tabular('Epoch', epoch)
            logger.log_tabular('EpRet', with_min_and_max=True)
            logger.log_tabular('TestEpRet', with_min_and_max=True)
            logger.log_tabular('EpLen', average_only=True)
            logger.log_tabular('TestEpLen', average_only=True)
            logger.log_tabular('TotalEnvInteracts', t)
            logger.log_tabular('Q1Vals', with_min_and_max=True)
            logger.log_tabular('Q2Vals', with_min_and_max=True)
            logger.log_tabular('LossPi', average_only=True)
            logger.log_tabular('LossQ', average_only=True)
            logger.log_tabular('Time', time.time()-start_time)
            logger.dump_tabular()

if __name__ == '__main__':
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('--env', type=str, default='HalfCheetah-v2')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/exercises/tf1/problem_set_1/exercise1_3.py [345:372]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if (t+1) % steps_per_epoch == 0:
            epoch = (t+1) // steps_per_epoch

            # Save model
            if (epoch % save_freq == 0) or (epoch == epochs):
                logger.save_state({'env': env}, None)

            # Test the performance of the deterministic version of the agent.
            test_agent()

            # Log info about epoch
            logger.log_tabular('Epoch', epoch)
            logger.log_tabular('EpRet', with_min_and_max=True)
            logger.log_tabular('TestEpRet', with_min_and_max=True)
            logger.log_tabular('EpLen', average_only=True)
            logger.log_tabular('TestEpLen', average_only=True)
            logger.log_tabular('TotalEnvInteracts', t)
            logger.log_tabular('Q1Vals', with_min_and_max=True)
            logger.log_tabular('Q2Vals', with_min_and_max=True)
            logger.log_tabular('LossPi', average_only=True)
            logger.log_tabular('LossQ', average_only=True)
            logger.log_tabular('Time', time.time()-start_time)
            logger.dump_tabular()

if __name__ == '__main__':
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('--env', type=str, default='HalfCheetah-v2')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -