{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.42006388306617737, "min": 0.4001881778240204, "max": 1.0226112604141235, "count": 180 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4334.21923828125, "min": 3899.380126953125, "max": 10461.3134765625, "count": 180 }, "SnowballTarget.Step.mean": { "value": 1999968.0, "min": 209936.0, "max": 1999968.0, "count": 180 }, "SnowballTarget.Step.sum": { "value": 1999968.0, "min": 209936.0, "max": 1999968.0, "count": 180 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.270292282104492, "min": 11.798823356628418, "max": 14.552634239196777, "count": 180 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2911.1396484375, "min": 2303.447998046875, "max": 2983.2900390625, "count": 180 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 180 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 180 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07010941528098877, "min": 0.05930819391627949, "max": 0.07843405551815807, "count": 180 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35054707640494387, "min": 0.2377243166510929, "max": 0.3921702775907904, "count": 180 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16052074736239863, "min": 0.132761103849785, "max": 0.22644827617149726, "count": 180 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8026037368119932, "min": 0.53104441539914, "max": 1.1322413808574863, "count": 180 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.16499761199997e-07, "min": 7.16499761199997e-07, "max": 0.00026917141027619996, "count": 180 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.582498805999985e-06, "min": 3.582498805999985e-06, "max": 0.0013384320538559998, "count": 180 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1002388, "min": 0.1002388, "max": 0.1897238, "count": 180 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.501194, "min": 0.40293520000000005, "max": 0.9461439999999999, "count": 180 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1916119999999956e-05, "min": 2.1916119999999956e-05, "max": 0.00448721762, "count": 180 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010958059999999978, "min": 0.00010958059999999978, "max": 0.022312585599999997, "count": 180 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.272727272727273, "min": 22.522727272727273, "max": 28.618181818181817, "count": 180 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1555.0, "min": 991.0, "max": 1574.0, "count": 180 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.272727272727273, "min": 22.522727272727273, "max": 28.618181818181817, "count": 180 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1555.0, "min": 991.0, "max": 1574.0, "count": 180 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 180 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 180 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679201223", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume", "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": "1679205238" }, "total": 4015.240720519, "count": 1, "self": 0.43275698100023874, "children": { "run_training.setup": { "total": 0.09888846699959686, "count": 1, "self": 0.09888846699959686 }, "TrainerController.start_learning": { "total": 4014.7090750710004, "count": 1, "self": 4.71832054284323, "children": { "TrainerController._reset_env": { "total": 5.659111906999897, "count": 1, "self": 5.659111906999897 }, "TrainerController.advance": { "total": 4004.1981672151574, "count": 163674, "self": 2.526422040025409, "children": { "env_step": { "total": 4001.671745175132, "count": 163674, "self": 2892.840898169175, "children": { "SubprocessEnvManager._take_step": { "total": 1106.4984949000418, "count": 163674, "self": 18.84952482197332, "children": { "TorchPolicy.evaluate": { "total": 1087.6489700780685, "count": 163674, "self": 1087.6489700780685 } } }, "workers": { "total": 2.332352105915106, "count": 163674, "self": 0.0, "children": { "worker_root": { "total": 4003.2350350009165, "count": 163674, "is_parallel": true, "self": 1890.5377339919942, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018879219996961183, "count": 1, "is_parallel": true, "self": 0.000592881999182282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012950400005138363, "count": 10, "is_parallel": true, "self": 0.0012950400005138363 } } }, "UnityEnvironment.step": { "total": 0.034174099000210845, "count": 1, "is_parallel": true, "self": 0.0006893470003888069, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038115799998195143, "count": 1, "is_parallel": true, "self": 0.00038115799998195143 }, "communicator.exchange": { "total": 0.030933258999993996, "count": 1, "is_parallel": true, "self": 0.030933258999993996 }, "steps_from_proto": { "total": 0.002170334999846091, "count": 1, "is_parallel": true, "self": 0.0004783879990100104, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016919470008360804, "count": 10, "is_parallel": true, "self": 0.0016919470008360804 } } } } } } }, "UnityEnvironment.step": { "total": 2112.6973010089223, "count": 163673, "is_parallel": true, "self": 83.50783148883147, "children": { "UnityEnvironment._generate_step_input": { "total": 44.78645162088287, "count": 163673, "is_parallel": true, "self": 44.78645162088287 }, "communicator.exchange": { "total": 1713.159306039065, "count": 163673, "is_parallel": true, "self": 1713.159306039065 }, "steps_from_proto": { "total": 271.24371186014287, "count": 163673, "is_parallel": true, "self": 52.68720711913238, "children": { "_process_rank_one_or_two_observation": { "total": 218.55650474101049, "count": 1636730, "is_parallel": true, "self": 218.55650474101049 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001982789999601664, "count": 1, "self": 0.0001982789999601664, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3974.8836340395733, "count": 3568782, "is_parallel": true, "self": 85.5665882126641, "children": { "process_trajectory": { "total": 2183.3365064108993, "count": 3568782, "is_parallel": true, "self": 2174.2487073949014, "children": { "RLTrainer._checkpoint": { "total": 9.087799015997916, "count": 36, "is_parallel": true, "self": 9.087799015997916 } } }, "_update_policy": { "total": 1705.9805394160098, "count": 818, "is_parallel": true, "self": 640.6093947930644, "children": { "TorchPPOOptimizer.update": { "total": 1065.3711446229454, "count": 41715, "is_parallel": true, "self": 1065.3711446229454 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13327712699992844, "count": 1, "self": 0.001997130999370711, "children": { "RLTrainer._checkpoint": { "total": 0.13127999600055773, "count": 1, "self": 0.13127999600055773 } } } } } } }