{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9074764847755432, "min": 0.8980207443237305, "max": 2.887725353240967, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4102.701171875, "min": 4102.701171875, "max": 16009.548828125, "count": 40 }, "SnowballTarget.Step.mean": { "value": 199920.0, "min": 4976.0, "max": 199920.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 199920.0, "min": 4976.0, "max": 199920.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.52747631072998, "min": 0.09490196406841278, "max": 12.592220306396484, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 901.978271484375, "min": 6.83294153213501, "max": 1038.786865234375, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 6567.0, "min": 4378.0, "max": 6567.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07068405189210727, "min": 0.06319188880186309, "max": 0.07711656137079818, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.14136810378421455, "min": 0.12638377760372618, "max": 0.22135205152216098, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20135490622590568, "min": 0.10407538581091691, "max": 0.2827119831653202, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.40270981245181137, "min": 0.20815077162183382, "max": 0.7716041477287517, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.782098406000002e-06, "min": 4.782098406000002e-06, "max": 0.000295182001606, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.564196812000005e-06, "min": 9.564196812000005e-06, "max": 0.0008211960262679999, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10239100000000001, "min": 0.10239100000000001, "max": 0.24759100000000003, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20478200000000002, "min": 0.20478200000000002, "max": 0.7105980000000001, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.954060000000004e-05, "min": 8.954060000000004e-05, "max": 0.004919860599999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00017908120000000008, "min": 0.00017908120000000008, "max": 0.0136892268, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.772727272727273, "min": 2.8636363636363638, "max": 25.09090909090909, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 545.0, "min": 63.0, "max": 808.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.772727272727273, "min": 2.8636363636363638, "max": 25.09090909090909, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 545.0, "min": 63.0, "max": 808.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689914868", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1689915421" }, "total": 552.590371831, "count": 1, "self": 0.8758308999999826, "children": { "run_training.setup": { "total": 0.03300840200006405, "count": 1, "self": 0.03300840200006405 }, "TrainerController.start_learning": { "total": 551.6815325289999, "count": 1, "self": 0.6336164739990409, "children": { "TrainerController._reset_env": { "total": 6.078368554999997, "count": 1, "self": 6.078368554999997 }, "TrainerController.advance": { "total": 544.7398578980009, "count": 18218, "self": 0.30483696400312965, "children": { "env_step": { "total": 544.4350209339977, "count": 18218, "self": 397.6144213920046, "children": { "SubprocessEnvManager._take_step": { "total": 146.50968025798602, "count": 18218, "self": 1.9840145679867192, "children": { "TorchPolicy.evaluate": { "total": 144.5256656899993, "count": 18218, "self": 144.5256656899993 } } }, "workers": { "total": 0.3109192840071273, "count": 18218, "self": 0.0, "children": { "worker_root": { "total": 549.7212558960065, "count": 18218, "is_parallel": true, "self": 284.3714180130047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0063523060000534315, "count": 1, "is_parallel": true, "self": 0.004795859000068958, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015564469999844732, "count": 10, "is_parallel": true, "self": 0.0015564469999844732 } } }, "UnityEnvironment.step": { "total": 0.0849465590000591, "count": 1, "is_parallel": true, "self": 0.0009313829999655354, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004525500000909233, "count": 1, "is_parallel": true, "self": 0.0004525500000909233 }, "communicator.exchange": { "total": 0.08036101599998347, "count": 1, "is_parallel": true, "self": 0.08036101599998347 }, "steps_from_proto": { "total": 0.0032016100000191727, "count": 1, "is_parallel": true, "self": 0.0007062609996637548, "children": { "_process_rank_one_or_two_observation": { "total": 0.002495349000355418, "count": 10, "is_parallel": true, "self": 0.002495349000355418 } } } } } } }, "UnityEnvironment.step": { "total": 265.3498378830018, "count": 18217, "is_parallel": true, "self": 11.18796804900171, "children": { "UnityEnvironment._generate_step_input": { "total": 5.470085376996963, "count": 18217, "is_parallel": true, "self": 5.470085376996963 }, "communicator.exchange": { "total": 212.13326891400357, "count": 18217, "is_parallel": true, "self": 212.13326891400357 }, "steps_from_proto": { "total": 36.558515542999544, "count": 18217, "is_parallel": true, "self": 7.096372885992309, "children": { "_process_rank_one_or_two_observation": { "total": 29.462142657007234, "count": 182170, "is_parallel": true, "self": 29.462142657007234 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00027281200004836137, "count": 1, "self": 0.00027281200004836137, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 541.8961593720343, "count": 354203, "is_parallel": true, "self": 7.870481475088809, "children": { "process_trajectory": { "total": 215.14901628794598, "count": 354203, "is_parallel": true, "self": 210.52944220694633, "children": { "RLTrainer._checkpoint": { "total": 4.619574080999655, "count": 20, "is_parallel": true, "self": 4.619574080999655 } } }, "_update_policy": { "total": 318.8766616089995, "count": 90, "is_parallel": true, "self": 125.46813759000077, "children": { "TorchPPOOptimizer.update": { "total": 193.40852401899872, "count": 7645, "is_parallel": true, "self": 193.40852401899872 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2294167899999593, "count": 1, "self": 0.0010001840000768425, "children": { "RLTrainer._checkpoint": { "total": 0.22841660599988245, "count": 1, "self": 0.22841660599988245 } } } } } } }