{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7248296737670898, "min": 0.6775791049003601, "max": 2.8754336833953857, "count": 60 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7367.1689453125, "min": 6802.60693359375, "max": 29478.9453125, "count": 60 }, "SnowballTarget.Step.mean": { "value": 599936.0, "min": 9952.0, "max": 599936.0, "count": 60 }, "SnowballTarget.Step.sum": { "value": 599936.0, "min": 9952.0, "max": 599936.0, "count": 60 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.834306716918945, "min": 0.29210716485977173, "max": 13.961349487304688, "count": 60 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2683.85546875, "min": 56.668792724609375, "max": 2850.8193359375, "count": 60 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 60 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 60 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06631343917529996, "min": 0.06228988266529461, "max": 0.07569344408739376, "count": 60 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2652537567011998, "min": 0.24915953066117844, "max": 0.3784672204369688, "count": 60 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15818140031222036, "min": 0.09367230314505744, "max": 0.2929079496100837, "count": 60 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6327256012488814, "min": 0.37468921258022975, "max": 1.323321575043248, "count": 60 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.4940991686666686e-06, "min": 2.4940991686666686e-06, "max": 0.00029729400090199997, "count": 60 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.976396674666675e-06, "min": 9.976396674666675e-06, "max": 0.00146172001276, "count": 60 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10083133333333334, "min": 0.10083133333333334, "max": 0.19909800000000002, "count": 60 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40332533333333337, "min": 0.40332533333333337, "max": 0.9872400000000001, "count": 60 }, "SnowballTarget.Policy.Beta.mean": { "value": 5.148353333333336e-05, "min": 5.148353333333336e-05, "max": 0.0049549902, "count": 60 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00020593413333333345, "min": 0.00020593413333333345, "max": 0.024363276, "count": 60 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.022727272727273, "min": 2.772727272727273, "max": 27.327272727272728, "count": 60 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1189.0, "min": 122.0, "max": 1503.0, "count": 60 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.022727272727273, "min": 2.772727272727273, "max": 27.327272727272728, "count": 60 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1189.0, "min": 122.0, "max": 1503.0, "count": 60 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679314522", "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 --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": "1679315886" }, "total": 1364.0446387240002, "count": 1, "self": 0.4338314750000336, "children": { "run_training.setup": { "total": 0.11963858699999719, "count": 1, "self": 0.11963858699999719 }, "TrainerController.start_learning": { "total": 1363.491168662, "count": 1, "self": 1.7064734049852177, "children": { "TrainerController._reset_env": { "total": 9.982239085999993, "count": 1, "self": 9.982239085999993 }, "TrainerController.advance": { "total": 1351.672203885015, "count": 54601, "self": 0.8388275130123475, "children": { "env_step": { "total": 1350.8333763720027, "count": 54601, "self": 980.8229017299849, "children": { "SubprocessEnvManager._take_step": { "total": 369.20415079601764, "count": 54601, "self": 6.335727415021495, "children": { "TorchPolicy.evaluate": { "total": 362.86842338099615, "count": 54601, "self": 362.86842338099615 } } }, "workers": { "total": 0.8063238460001685, "count": 54601, "self": 0.0, "children": { "worker_root": { "total": 1359.0819031600113, "count": 54601, "is_parallel": true, "self": 637.0596981149951, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005475850000010496, "count": 1, "is_parallel": true, "self": 0.00373308699994368, "children": { "_process_rank_one_or_two_observation": { "total": 0.001742763000066816, "count": 10, "is_parallel": true, "self": 0.001742763000066816 } } }, "UnityEnvironment.step": { "total": 0.035366794999987405, "count": 1, "is_parallel": true, "self": 0.0005652750000137985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002833429999782311, "count": 1, "is_parallel": true, "self": 0.0002833429999782311 }, "communicator.exchange": { "total": 0.03272804499999893, "count": 1, "is_parallel": true, "self": 0.03272804499999893 }, "steps_from_proto": { "total": 0.0017901319999964471, "count": 1, "is_parallel": true, "self": 0.00037849499994990765, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014116370000465395, "count": 10, "is_parallel": true, "self": 0.0014116370000465395 } } } } } } }, "UnityEnvironment.step": { "total": 722.0222050450162, "count": 54600, "is_parallel": true, "self": 28.610750178040803, "children": { "UnityEnvironment._generate_step_input": { "total": 15.462808761952402, "count": 54600, "is_parallel": true, "self": 15.462808761952402 }, "communicator.exchange": { "total": 585.9845247029803, "count": 54600, "is_parallel": true, "self": 585.9845247029803 }, "steps_from_proto": { "total": 91.96412140204285, "count": 54600, "is_parallel": true, "self": 18.332462579085444, "children": { "_process_rank_one_or_two_observation": { "total": 73.6316588229574, "count": 546000, "is_parallel": true, "self": 73.6316588229574 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00035181799989914, "count": 1, "self": 0.00035181799989914, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1342.3251433950538, "count": 1186847, "is_parallel": true, "self": 28.085934761043745, "children": { "process_trajectory": { "total": 740.5974856450091, "count": 1186847, "is_parallel": true, "self": 736.9875699670091, "children": { "RLTrainer._checkpoint": { "total": 3.609915677999993, "count": 12, "is_parallel": true, "self": 3.609915677999993 } } }, "_update_policy": { "total": 573.6417229890011, "count": 272, "is_parallel": true, "self": 210.1120015600037, "children": { "TorchPPOOptimizer.update": { "total": 363.5297214289974, "count": 13869, "is_parallel": true, "self": 363.5297214289974 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1299004679999598, "count": 1, "self": 0.0009268559999782156, "children": { "RLTrainer._checkpoint": { "total": 0.12897361199998159, "count": 1, "self": 0.12897361199998159 } } } } } } }