{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8923442363739014, "min": 0.8923442363739014, "max": 2.8903186321258545, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9158.12890625, "min": 8653.87890625, "max": 29695.134765625, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.374176025390625, "min": -0.00461520254611969, "max": 14.383991241455078, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2946.7060546875, "min": -0.8953492641448975, "max": 2948.71826171875, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.527272727272727, "min": 2.522727272727273, "max": 28.654545454545456, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1569.0, "min": 111.0, "max": 1576.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.527272727272727, "min": 2.522727272727273, "max": 28.654545454545456, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1569.0, "min": 111.0, "max": 1576.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06086980885779345, "min": 0.058823424854147564, "max": 0.07065732356816419, "count": 97 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06086980885779345, "min": 0.058823424854147564, "max": 0.07065732356816419, "count": 97 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1482402557563601, "min": 0.08072170176313427, "max": 0.2968664024062831, "count": 97 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1482402557563601, "min": 0.08072170176313427, "max": 0.2968664024062831, "count": 97 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.244499585200012e-06, "min": 1.244499585200012e-06, "max": 0.00029692440102520003, "count": 97 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.244499585200012e-06, "min": 1.244499585200012e-06, "max": 0.00029692440102520003, "count": 97 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10041480000000001, "min": 0.10041480000000001, "max": 0.1989748, "count": 97 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10041480000000001, "min": 0.10041480000000001, "max": 0.1989748, "count": 97 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.06985200000002e-05, "min": 3.06985200000002e-05, "max": 0.004948842519999999, "count": 97 }, "SnowballTarget.Policy.Beta.sum": { "value": 3.06985200000002e-05, "min": 3.06985200000002e-05, "max": 0.004948842519999999, "count": 97 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685387356", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685392104" }, "total": 4747.500766848, "count": 1, "self": 0.48841547000029095, "children": { "run_training.setup": { "total": 0.04340411699990909, "count": 1, "self": 0.04340411699990909 }, "TrainerController.start_learning": { "total": 4746.968947261, "count": 1, "self": 5.114859669081852, "children": { "TrainerController._reset_env": { "total": 3.991836987999932, "count": 1, "self": 3.991836987999932 }, "TrainerController.advance": { "total": 4737.725261504917, "count": 181872, "self": 2.62865422302184, "children": { "env_step": { "total": 4735.096607281896, "count": 181872, "self": 3594.658866705777, "children": { "SubprocessEnvManager._take_step": { "total": 1137.8589556881113, "count": 181872, "self": 21.233470379049777, "children": { "TorchPolicy.evaluate": { "total": 1116.6254853090616, "count": 181872, "self": 1116.6254853090616 } } }, "workers": { "total": 2.5787848880070214, "count": 181872, "self": 0.0, "children": { "worker_root": { "total": 4733.518990897057, "count": 181872, "is_parallel": true, "self": 2290.3763285820314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005748607000214179, "count": 1, "is_parallel": true, "self": 0.004062546000113798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016860610001003806, "count": 10, "is_parallel": true, "self": 0.0016860610001003806 } } }, "UnityEnvironment.step": { "total": 0.03698387500003264, "count": 1, "is_parallel": true, "self": 0.0006701680001697241, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032914300004449615, "count": 1, "is_parallel": true, "self": 0.00032914300004449615 }, "communicator.exchange": { "total": 0.033594622999999046, "count": 1, "is_parallel": true, "self": 0.033594622999999046 }, "steps_from_proto": { "total": 0.0023899409998193732, "count": 1, "is_parallel": true, "self": 0.00040843199963092047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019815090001884528, "count": 10, "is_parallel": true, "self": 0.0019815090001884528 } } } } } } }, "UnityEnvironment.step": { "total": 2443.1426623150255, "count": 181871, "is_parallel": true, "self": 105.44505381493855, "children": { "UnityEnvironment._generate_step_input": { "total": 52.89960010097252, "count": 181871, "is_parallel": true, "self": 52.89960010097252 }, "communicator.exchange": { "total": 1934.1572663770094, "count": 181871, "is_parallel": true, "self": 1934.1572663770094 }, "steps_from_proto": { "total": 350.6407420221051, "count": 181871, "is_parallel": true, "self": 63.7596964997465, "children": { "_process_rank_one_or_two_observation": { "total": 286.8810455223586, "count": 1818710, "is_parallel": true, "self": 286.8810455223586 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033434100078011397, "count": 1, "self": 0.00033434100078011397, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4678.9930856826795, "count": 6279853, "is_parallel": true, "self": 152.8643107338885, "children": { "process_trajectory": { "total": 3473.1756873387912, "count": 6279853, "is_parallel": true, "self": 3462.034507245793, "children": { "RLTrainer._checkpoint": { "total": 11.141180092997956, "count": 40, "is_parallel": true, "self": 11.141180092997956 } } }, "_update_policy": { "total": 1052.9530876099998, "count": 97, "is_parallel": true, "self": 584.6118025519165, "children": { "TorchPPOOptimizer.update": { "total": 468.34128505808326, "count": 38217, "is_parallel": true, "self": 468.34128505808326 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13665475800007698, "count": 1, "self": 0.0008705879999979516, "children": { "RLTrainer._checkpoint": { "total": 0.13578417000007903, "count": 1, "self": 0.13578417000007903 } } } } } } }