{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8896782398223877, "min": 2.8896782398223877, "max": 2.890336751937866, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 27622.43359375, "min": 27433.9375, "max": 29818.41796875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15598002076148987, "min": 0.0047662751749157906, "max": 0.16870032250881195, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 30.416105270385742, "min": 0.9246573448181152, "max": 34.58356475830078, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06415645566948133, "min": 0.06399432363946735, "max": 0.07360126287676394, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25662582267792533, "min": 0.2559772945578694, "max": 0.3616826339127204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.0472514656025405, "min": 0.03612691259888165, "max": 0.06508046232264343, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.189005862410162, "min": 0.1445076503955266, "max": 0.26688022831199215, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.091730600000007e-08, "min": 8.091730600000007e-08, "max": 2.918822706e-06, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.236692240000003e-07, "min": 3.236692240000003e-07, "max": 1.3851638279999999e-05, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 3.3181818181818183, "min": 2.3777777777777778, "max": 3.3181818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 146.0, "min": 107.0, "max": 176.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 3.3181818181818183, "min": 2.3777777777777778, "max": 3.3181818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 146.0, "min": 107.0, "max": 176.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691785540", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1691786061" }, "total": 520.9244606269999, "count": 1, "self": 0.4931045139996968, "children": { "run_training.setup": { "total": 0.06581045600000834, "count": 1, "self": 0.06581045600000834 }, "TrainerController.start_learning": { "total": 520.3655456570002, "count": 1, "self": 0.6444751849940076, "children": { "TrainerController._reset_env": { "total": 5.073664254999812, "count": 1, "self": 5.073664254999812 }, "TrainerController.advance": { "total": 514.4944833930062, "count": 18201, "self": 0.3376619700034098, "children": { "env_step": { "total": 514.1568214230028, "count": 18201, "self": 375.03920087500114, "children": { "SubprocessEnvManager._take_step": { "total": 138.78077767699142, "count": 18201, "self": 2.055499486009012, "children": { "TorchPolicy.evaluate": { "total": 136.7252781909824, "count": 18201, "self": 136.7252781909824 } } }, "workers": { "total": 0.3368428710102762, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 518.4026777910015, "count": 18201, "is_parallel": true, "self": 243.52079856098862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007281914000031975, "count": 1, "is_parallel": true, "self": 0.0049838659999750234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022980480000569514, "count": 10, "is_parallel": true, "self": 0.0022980480000569514 } } }, "UnityEnvironment.step": { "total": 0.040112281999881816, "count": 1, "is_parallel": true, "self": 0.0006382570002188004, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003672420000384591, "count": 1, "is_parallel": true, "self": 0.0003672420000384591 }, "communicator.exchange": { "total": 0.036837975999787886, "count": 1, "is_parallel": true, "self": 0.036837975999787886 }, "steps_from_proto": { "total": 0.00226880699983667, "count": 1, "is_parallel": true, "self": 0.00043515799984561454, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018336489999910555, "count": 10, "is_parallel": true, "self": 0.0018336489999910555 } } } } } } }, "UnityEnvironment.step": { "total": 274.8818792300128, "count": 18200, "is_parallel": true, "self": 11.577232592019072, "children": { "UnityEnvironment._generate_step_input": { "total": 5.9928607519805155, "count": 18200, "is_parallel": true, "self": 5.9928607519805155 }, "communicator.exchange": { "total": 216.49744649901754, "count": 18200, "is_parallel": true, "self": 216.49744649901754 }, "steps_from_proto": { "total": 40.8143393869957, "count": 18200, "is_parallel": true, "self": 7.838683240930322, "children": { "_process_rank_one_or_two_observation": { "total": 32.975656146065376, "count": 182000, "is_parallel": true, "self": 32.975656146065376 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012842900014220504, "count": 1, "self": 0.00012842900014220504, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 510.10041741493774, "count": 491033, "is_parallel": true, "self": 11.649732775948223, "children": { "process_trajectory": { "total": 281.4376397579906, "count": 491033, "is_parallel": true, "self": 280.605716058991, "children": { "RLTrainer._checkpoint": { "total": 0.831923698999617, "count": 4, "is_parallel": true, "self": 0.831923698999617 } } }, "_update_policy": { "total": 217.0130448809989, "count": 90, "is_parallel": true, "self": 87.36269089900338, "children": { "TorchPPOOptimizer.update": { "total": 129.65035398199552, "count": 4587, "is_parallel": true, "self": 129.65035398199552 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1527943950000008, "count": 1, "self": 0.0009562760001244897, "children": { "RLTrainer._checkpoint": { "total": 0.15183811899987631, "count": 1, "self": 0.15183811899987631 } } } } } } }