spinup/exercises/pytorch/problem_set_1/exercise1_3.py [367:404]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        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')
    parser.add_argument('--seed', '-s', type=int, default=0)
    parser.add_argument('--exp_name', type=str, default='ex13-td3')
    parser.add_argument('--use_soln', action='store_true')
    args = parser.parse_args()

    from spinup.utils.run_utils import setup_logger_kwargs
    logger_kwargs = setup_logger_kwargs(args.exp_name + '-' + args.env.lower(), args.seed)

    all_kwargs = dict(
        env_fn=lambda : gym.make(args.env), 
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/exercises/tf1/problem_set_1/exercise1_3.py [345:382]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        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')
    parser.add_argument('--seed', '-s', type=int, default=0)
    parser.add_argument('--exp_name', type=str, default='ex13-td3')
    parser.add_argument('--use_soln', action='store_true')
    args = parser.parse_args()

    from spinup.utils.run_utils import setup_logger_kwargs
    logger_kwargs = setup_logger_kwargs(args.exp_name + '-' + args.env.lower(), args.seed)

    all_kwargs = dict(
        env_fn=lambda : gym.make(args.env), 
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -