{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8993253111839294, "min": 0.8993253111839294, "max": 2.690913200378418, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8626.328125, "min": 8626.328125, "max": 25929.640625, "count": 19 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.297964096069336, "min": 1.6166577339172363, "max": 12.297964096069336, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2398.10302734375, "min": 290.9983825683594, "max": 2476.78173828125, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06330455137225834, "min": 0.06139311952460511, "max": 0.07539112391646532, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25321820548903334, "min": 0.24557247809842045, "max": 0.3527025357820379, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20547234577437243, "min": 0.18475318345807346, "max": 0.30519769968939764, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8218893830974897, "min": 0.7390127338322938, "max": 1.5259884984469883, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.00027551400816199997, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.00123732008756, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.191838, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.41095200000000004, "max": 0.9124400000000001, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.0045927162, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.020630756, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.40909090909091, "min": 7.659090909090909, "max": 24.40909090909091, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1074.0, "min": 337.0, "max": 1321.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.40909090909091, "min": 7.659090909090909, "max": 24.40909090909091, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1074.0, "min": 337.0, "max": 1321.0, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685009499", "python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]", "command_line_arguments": "/home/stephen/miniconda3/envs/deep-rl-course/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --resume --width=1280 --height=720 --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1685009758" }, "total": 259.0191323790059, "count": 1, "self": 0.2695951179921394, "children": { "run_training.setup": { "total": 0.01197313801094424, "count": 1, "self": 0.01197313801094424 }, "TrainerController.start_learning": { "total": 258.7375641230028, "count": 1, "self": 0.399064487835858, "children": { "TrainerController._reset_env": { "total": 6.2491597949992865, "count": 1, "self": 6.2491597949992865 }, "TrainerController.advance": { "total": 251.9837565281632, "count": 17208, "self": 0.18344777317543048, "children": { "env_step": { "total": 251.80030875498778, "count": 17208, "self": 175.5491361827444, "children": { "SubprocessEnvManager._take_step": { "total": 76.0442439661565, "count": 17208, "self": 0.948231075934018, "children": { "TorchPolicy.evaluate": { "total": 75.09601289022248, "count": 17208, "self": 75.09601289022248 } } }, "workers": { "total": 0.20692860608687624, "count": 17208, "self": 0.0, "children": { "worker_root": { "total": 258.19789130035497, "count": 17208, "is_parallel": true, "self": 141.11056553387607, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011972069914918393, "count": 1, "is_parallel": true, "self": 0.0003728490410139784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008243579504778609, "count": 10, "is_parallel": true, "self": 0.0008243579504778609 } } }, "UnityEnvironment.step": { "total": 0.017853333003586158, "count": 1, "is_parallel": true, "self": 0.00029249899671413004, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019724000594578683, "count": 1, "is_parallel": true, "self": 0.00019724000594578683 }, "communicator.exchange": { "total": 0.016355291998479515, "count": 1, "is_parallel": true, "self": 0.016355291998479515 }, "steps_from_proto": { "total": 0.001008302002446726, "count": 1, "is_parallel": true, "self": 0.00020531401969492435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008029879827518016, "count": 10, "is_parallel": true, "self": 0.0008029879827518016 } } } } } } }, "UnityEnvironment.step": { "total": 117.0873257664789, "count": 17207, "is_parallel": true, "self": 5.3620431042218115, "children": { "UnityEnvironment._generate_step_input": { "total": 2.91024270321941, "count": 17207, "is_parallel": true, "self": 2.91024270321941 }, "communicator.exchange": { "total": 92.03167788419523, "count": 17207, "is_parallel": true, "self": 92.03167788419523 }, "steps_from_proto": { "total": 16.783362074842444, "count": 17207, "is_parallel": true, "self": 3.238200179708656, "children": { "_process_rank_one_or_two_observation": { "total": 13.545161895133788, "count": 172070, "is_parallel": true, "self": 13.545161895133788 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.981299571227282e-05, "count": 1, "self": 4.981299571227282e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 251.59374435238715, "count": 187162, "is_parallel": true, "self": 1.784236219653394, "children": { "process_trajectory": { "total": 141.0963138907391, "count": 187162, "is_parallel": true, "self": 140.6034324937209, "children": { "RLTrainer._checkpoint": { "total": 0.4928813970182091, "count": 4, "is_parallel": true, "self": 0.4928813970182091 } } }, "_update_policy": { "total": 108.71319424199464, "count": 85, "is_parallel": true, "self": 27.92362355730438, "children": { "TorchPPOOptimizer.update": { "total": 80.78957068469026, "count": 4332, "is_parallel": true, "self": 80.78957068469026 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10553349900874309, "count": 1, "self": 0.0007183550042100251, "children": { "RLTrainer._checkpoint": { "total": 0.10481514400453307, "count": 1, "self": 0.10481514400453307 } } } } } } }