{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7296169400215149, "min": 0.7296169400215149, "max": 2.8619449138641357, "count": 69 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7022.56298828125, "min": 7022.56298828125, "max": 29372.140625, "count": 69 }, "SnowballTarget.Step.mean": { "value": 689944.0, "min": 9952.0, "max": 689944.0, "count": 69 }, "SnowballTarget.Step.sum": { "value": 689944.0, "min": 9952.0, "max": 689944.0, "count": 69 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.233765602111816, "min": 0.44250762462615967, "max": 14.233765602111816, "count": 69 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2761.3505859375, "min": 85.84648132324219, "max": 2896.015625, "count": 69 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 69 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 69 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06606371616533793, "min": 0.058183996234826424, "max": 0.07496194352650348, "count": 69 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26425486466135173, "min": 0.2327359849393057, "max": 0.36537159989748214, "count": 69 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14776242465949527, "min": 0.12730362003112175, "max": 0.2570725197301192, "count": 69 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5910496986379811, "min": 0.509214480124487, "max": 1.2853625986505959, "count": 69 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.0001972182342606, "min": 0.0001972182342606, "max": 0.00029918820027059994, "count": 69 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0007888729370424, "min": 0.0007888729370424, "max": 0.0014885160038279998, "count": 69 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1657394, "min": 0.1657394, "max": 0.1997294, "count": 69 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6629576, "min": 0.6629576, "max": 0.996172, "count": 69 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00329039606, "min": 0.00329039606, "max": 0.004986497059999999, "count": 69 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.01316158424, "min": 0.01316158424, "max": 0.024808982800000004, "count": 69 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.477272727272727, "min": 3.590909090909091, "max": 28.072727272727274, "count": 69 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1209.0, "min": 158.0, "max": 1544.0, "count": 69 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.477272727272727, "min": 3.590909090909091, "max": 28.072727272727274, "count": 69 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1209.0, "min": 158.0, "max": 1544.0, "count": 69 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 69 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 69 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676820803", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676822322" }, "total": 1519.214550405, "count": 1, "self": 0.2439219919997413, "children": { "run_training.setup": { "total": 0.1081719919999955, "count": 1, "self": 0.1081719919999955 }, "TrainerController.start_learning": { "total": 1518.8624564210002, "count": 1, "self": 1.7947699859996646, "children": { "TrainerController._reset_env": { "total": 9.54747650600001, "count": 1, "self": 9.54747650600001 }, "TrainerController.advance": { "total": 1507.3224612880003, "count": 63092, "self": 0.9414994479986944, "children": { "env_step": { "total": 1506.3809618400016, "count": 63092, "self": 1033.5765478970134, "children": { "SubprocessEnvManager._take_step": { "total": 471.9134027989863, "count": 63092, "self": 4.93957962602525, "children": { "TorchPolicy.evaluate": { "total": 466.97382317296103, "count": 63092, "self": 103.73208804996653, "children": { "TorchPolicy.sample_actions": { "total": 363.2417351229945, "count": 63092, "self": 363.2417351229945 } } } } }, "workers": { "total": 0.8910111440019364, "count": 63091, "self": 0.0, "children": { "worker_root": { "total": 1513.752513370998, "count": 63091, "is_parallel": true, "self": 721.1554334689783, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005570304999992004, "count": 1, "is_parallel": true, "self": 0.003334302000041589, "children": { "_process_rank_one_or_two_observation": { "total": 0.002236002999950415, "count": 10, "is_parallel": true, "self": 0.002236002999950415 } } }, "UnityEnvironment.step": { "total": 0.03414712599999348, "count": 1, "is_parallel": true, "self": 0.000542765000034251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003033830000163107, "count": 1, "is_parallel": true, "self": 0.0003033830000163107 }, "communicator.exchange": { "total": 0.03151544299998932, "count": 1, "is_parallel": true, "self": 0.03151544299998932 }, "steps_from_proto": { "total": 0.0017855349999535974, "count": 1, "is_parallel": true, "self": 0.00041315900006111406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013723759998924834, "count": 10, "is_parallel": true, "self": 0.0013723759998924834 } } } } } } }, "UnityEnvironment.step": { "total": 792.5970799020197, "count": 63090, "is_parallel": true, "self": 32.58894895700587, "children": { "UnityEnvironment._generate_step_input": { "total": 17.4296128529989, "count": 63090, "is_parallel": true, "self": 17.4296128529989 }, "communicator.exchange": { "total": 638.4919594439984, "count": 63090, "is_parallel": true, "self": 638.4919594439984 }, "steps_from_proto": { "total": 104.08655864801648, "count": 63090, "is_parallel": true, "self": 22.26571246707016, "children": { "_process_rank_one_or_two_observation": { "total": 81.82084618094632, "count": 630900, "is_parallel": true, "self": 81.82084618094632 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.68030000320141e-05, "count": 1, "self": 4.68030000320141e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1496.1477808018992, "count": 1367817, "is_parallel": true, "self": 33.682492238972145, "children": { "process_trajectory": { "total": 854.8324138249262, "count": 1367817, "is_parallel": true, "self": 851.6375654119264, "children": { "RLTrainer._checkpoint": { "total": 3.194848412999818, "count": 13, "is_parallel": true, "self": 3.194848412999818 } } }, "_update_policy": { "total": 607.632874738001, "count": 315, "is_parallel": true, "self": 207.1477557859875, "children": { "TorchPPOOptimizer.update": { "total": 400.48511895201347, "count": 16062, "is_parallel": true, "self": 400.48511895201347 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19770183800005725, "count": 1, "self": 0.001166247000128351, "children": { "RLTrainer._checkpoint": { "total": 0.1965355909999289, "count": 1, "self": 0.1965355909999289 } } } } } } }