{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3760979175567627, "min": 1.3741816282272339, "max": 2.8902549743652344, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13260.0791015625, "min": 13207.19140625, "max": 29726.2734375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 9.136834144592285, "min": 0.3254414498806, "max": 9.136834144592285, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1873.051025390625, "min": 63.135643005371094, "max": 1873.051025390625, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06475385620498428, "min": 0.06286513181471759, "max": 0.07484555288589463, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32376928102492136, "min": 0.25146052725887036, "max": 0.3741155668552143, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2671147185213426, "min": 0.10424534807474736, "max": 0.3020611020747353, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.335573592606713, "min": 0.41698139229898945, "max": 1.5103055103736764, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0185898240000011e-07, "min": 1.0185898240000011e-07, "max": 9.891761082400001e-06, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.092949120000005e-07, "min": 5.092949120000005e-07, "max": 4.846881531200001e-05, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.09999999999999998, "min": 0.09999999999999998, "max": 0.09999999999999998, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4999999999999999, "min": 0.3999999999999999, "max": 0.4999999999999999, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.8, "min": 2.75, "max": 17.944444444444443, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 979.0, "min": 121.0, "max": 979.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.8, "min": 2.75, "max": 17.944444444444443, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 979.0, "min": 121.0, "max": 979.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680120697", "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": "1680121988" }, "total": 1290.614038105, "count": 1, "self": 0.43066233599984116, "children": { "run_training.setup": { "total": 0.11490686000001915, "count": 1, "self": 0.11490686000001915 }, "TrainerController.start_learning": { "total": 1290.068468909, "count": 1, "self": 1.3333764230151246, "children": { "TrainerController._reset_env": { "total": 8.782255125999995, "count": 1, "self": 8.782255125999995 }, "TrainerController.advance": { "total": 1279.7556537879852, "count": 45481, "self": 0.6431004699741152, "children": { "env_step": { "total": 1279.1125533180111, "count": 45481, "self": 963.5343741919941, "children": { "SubprocessEnvManager._take_step": { "total": 314.9478709970116, "count": 45481, "self": 5.086730761011609, "children": { "TorchPolicy.evaluate": { "total": 309.861140236, "count": 45481, "self": 309.861140236 } } }, "workers": { "total": 0.6303081290054706, "count": 45481, "self": 0.0, "children": { "worker_root": { "total": 1286.471164869994, "count": 45481, "is_parallel": true, "self": 700.211626993969, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005581177000010484, "count": 1, "is_parallel": true, "self": 0.0040250610000498455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015561159999606389, "count": 10, "is_parallel": true, "self": 0.0015561159999606389 } } }, "UnityEnvironment.step": { "total": 0.03431064200003675, "count": 1, "is_parallel": true, "self": 0.0005597260000058668, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044923000007202063, "count": 1, "is_parallel": true, "self": 0.00044923000007202063 }, "communicator.exchange": { "total": 0.03146836899998107, "count": 1, "is_parallel": true, "self": 0.03146836899998107 }, "steps_from_proto": { "total": 0.0018333169999777965, "count": 1, "is_parallel": true, "self": 0.00040283899988935445, "children": { "_process_rank_one_or_two_observation": { "total": 0.001430478000088442, "count": 10, "is_parallel": true, "self": 0.001430478000088442 } } } } } } }, "UnityEnvironment.step": { "total": 586.259537876025, "count": 45480, "is_parallel": true, "self": 23.722367670039603, "children": { "UnityEnvironment._generate_step_input": { "total": 12.569993300012356, "count": 45480, "is_parallel": true, "self": 12.569993300012356 }, "communicator.exchange": { "total": 474.4221894120019, "count": 45480, "is_parallel": true, "self": 474.4221894120019 }, "steps_from_proto": { "total": 75.54498749397112, "count": 45480, "is_parallel": true, "self": 14.81360858498249, "children": { "_process_rank_one_or_two_observation": { "total": 60.73137890898863, "count": 454800, "is_parallel": true, "self": 60.73137890898863 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.8051000046834815e-05, "count": 1, "self": 3.8051000046834815e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1271.6577303780296, "count": 984762, "is_parallel": true, "self": 23.97319470004095, "children": { "process_trajectory": { "total": 613.9723629619871, "count": 984762, "is_parallel": true, "self": 609.0695376309872, "children": { "RLTrainer._checkpoint": { "total": 4.902825330999917, "count": 10, "is_parallel": true, "self": 4.902825330999917 } } }, "_update_policy": { "total": 633.7121727160015, "count": 227, "is_parallel": true, "self": 249.08239113001252, "children": { "TorchPPOOptimizer.update": { "total": 384.629781585989, "count": 19285, "is_parallel": true, "self": 384.629781585989 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1971455209998112, "count": 1, "self": 0.0025897619998431765, "children": { "RLTrainer._checkpoint": { "total": 0.19455575899996802, "count": 1, "self": 0.19455575899996802 } } } } } } }