{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9995797872543335, "min": 0.9995797872543335, "max": 2.8654611110687256, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10258.6875, "min": 9865.3837890625, "max": 29345.1875, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.867311477661133, "min": 0.33589786291122437, "max": 11.867311477661133, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2432.798828125, "min": 65.1641845703125, "max": 2432.798828125, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07569922789766946, "min": 0.0633215020616619, "max": 0.07569922789766946, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3784961394883473, "min": 0.2532860082466476, "max": 0.3784961394883473, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22119534582484005, "min": 0.12193118343951509, "max": 0.2691577225923538, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1059767291242002, "min": 0.48772473375806036, "max": 1.3441939333490296, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.629343007466667e-05, "min": 1.629343007466667e-05, "max": 0.000481960003608, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.146715037333334e-05, "min": 8.146715037333334e-05, "max": 0.0022448000510400003, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.19639199999999998, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.43943466666666664, "max": 0.94896, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.004819960799999999, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.072727272727274, "min": 3.4318181818181817, "max": 24.072727272727274, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1324.0, "min": 151.0, "max": 1324.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.072727272727274, "min": 3.4318181818181817, "max": 24.072727272727274, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1324.0, "min": 151.0, "max": 1324.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727500133", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget0 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727500513" }, "total": 379.9221389459999, "count": 1, "self": 0.7444355449999875, "children": { "run_training.setup": { "total": 0.07308690399986517, "count": 1, "self": 0.07308690399986517 }, "TrainerController.start_learning": { "total": 379.10461649700005, "count": 1, "self": 0.48666175800622113, "children": { "TrainerController._reset_env": { "total": 1.5965696440000556, "count": 1, "self": 1.5965696440000556 }, "TrainerController.advance": { "total": 376.88248668299366, "count": 13685, "self": 0.22151514896199842, "children": { "env_step": { "total": 376.66097153403166, "count": 13685, "self": 231.2596740380077, "children": { "SubprocessEnvManager._take_step": { "total": 145.17857908801284, "count": 13685, "self": 1.2053165370246006, "children": { "TorchPolicy.evaluate": { "total": 143.97326255098824, "count": 13685, "self": 143.97326255098824 } } }, "workers": { "total": 0.22271840801113285, "count": 13685, "self": 0.0, "children": { "worker_root": { "total": 378.0368525329968, "count": 13685, "is_parallel": true, "self": 199.70694334599898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002320639000117808, "count": 1, "is_parallel": true, "self": 0.0007448540002314985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015757849998863094, "count": 10, "is_parallel": true, "self": 0.0015757849998863094 } } }, "UnityEnvironment.step": { "total": 0.03778031799993187, "count": 1, "is_parallel": true, "self": 0.0007318539999232598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041128700013359776, "count": 1, "is_parallel": true, "self": 0.00041128700013359776 }, "communicator.exchange": { "total": 0.034428868999839324, "count": 1, "is_parallel": true, "self": 0.034428868999839324 }, "steps_from_proto": { "total": 0.002208308000035686, "count": 1, "is_parallel": true, "self": 0.00042110100002901163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017872070000066742, "count": 10, "is_parallel": true, "self": 0.0017872070000066742 } } } } } } }, "UnityEnvironment.step": { "total": 178.32990918699784, "count": 13684, "is_parallel": true, "self": 8.064627182002596, "children": { "UnityEnvironment._generate_step_input": { "total": 4.465439333007453, "count": 13684, "is_parallel": true, "self": 4.465439333007453 }, "communicator.exchange": { "total": 138.11344563599255, "count": 13684, "is_parallel": true, "self": 138.11344563599255 }, "steps_from_proto": { "total": 27.686397035995242, "count": 13684, "is_parallel": true, "self": 5.307548977951683, "children": { "_process_rank_one_or_two_observation": { "total": 22.37884805804356, "count": 136840, "is_parallel": true, "self": 22.37884805804356 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001841600001171173, "count": 1, "self": 0.0001841600001171173, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 371.8514794819125, "count": 566777, "is_parallel": true, "self": 12.726796213875332, "children": { "process_trajectory": { "total": 207.00011176003613, "count": 566777, "is_parallel": true, "self": 206.06839331103606, "children": { "RLTrainer._checkpoint": { "total": 0.9317184490000727, "count": 3, "is_parallel": true, "self": 0.9317184490000727 } } }, "_update_policy": { "total": 152.12457150800105, "count": 68, "is_parallel": true, "self": 49.18630655401034, "children": { "TorchPPOOptimizer.update": { "total": 102.93826495399071, "count": 3465, "is_parallel": true, "self": 102.93826495399071 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13871425199999976, "count": 1, "self": 0.00137598500009517, "children": { "RLTrainer._checkpoint": { "total": 0.1373382669999046, "count": 1, "self": 0.1373382669999046 } } } } } } }