{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9726230502128601, "min": 0.9726230502128601, "max": 2.598764657974243, "count": 4 }, "SnowballTarget.Policy.Entropy.sum": { "value": 48444.41015625, "min": 48444.41015625, "max": 131268.796875, "count": 4 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.712594032287598, "min": 2.5928256511688232, "max": 12.712594032287598, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 12623.60546875, "min": 2572.0830078125, "max": 12623.60546875, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 48158.0, "min": 48158.0, "max": 50347.0, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06775510830207274, "min": 0.06690546175835017, "max": 0.07053242674468498, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 1.4906123826456001, "min": 1.4719201586837038, "max": 1.6222458151277546, "count": 4 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20212012020050948, "min": 0.20212012020050948, "max": 0.2558277772083713, "count": 4 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.446642644411209, "min": 4.446642644411209, "max": 5.88403887579254, "count": 4 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.7782087406000005e-05, "min": 3.7782087406000005e-05, "max": 0.00026218201260600003, "count": 4 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.000831205922932, "min": 0.000831205922932, "max": 0.005768004277332, "count": 4 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.11259400000000003, "min": 0.11259400000000003, "max": 0.187394, "count": 4 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.4770680000000005, "min": 2.4770680000000005, "max": 4.122668, "count": 4 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0006384406, "min": 0.0006384406, "max": 0.0043709606, "count": 4 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.014045693199999999, "min": 0.014045693199999999, "max": 0.0961611332, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.301652892561982, "min": 8.805785123966942, "max": 25.301652892561982, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6123.0, "min": 2131.0, "max": 6123.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.301652892561982, "min": 8.805785123966942, "max": 25.301652892561982, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6123.0, "min": 2131.0, "max": 6123.0, "count": 4 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687874400", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1687874856" }, "total": 456.80333821599993, "count": 1, "self": 0.4294798869998431, "children": { "run_training.setup": { "total": 0.04117033200009246, "count": 1, "self": 0.04117033200009246 }, "TrainerController.start_learning": { "total": 456.332687997, "count": 1, "self": 0.5222430330115913, "children": { "TrainerController._reset_env": { "total": 4.876711627000077, "count": 1, "self": 4.876711627000077 }, "TrainerController.advance": { "total": 450.7930559909885, "count": 18204, "self": 0.24510790299495966, "children": { "env_step": { "total": 450.5479480879935, "count": 18204, "self": 327.78431326902523, "children": { "SubprocessEnvManager._take_step": { "total": 122.51350882597035, "count": 18204, "self": 1.7827979519695418, "children": { "TorchPolicy.evaluate": { "total": 120.7307108740008, "count": 18204, "self": 120.7307108740008 } } }, "workers": { "total": 0.2501259929979369, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 454.7216404259975, "count": 18204, "is_parallel": true, "self": 214.52291718998595, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056312019999040785, "count": 1, "is_parallel": true, "self": 0.004225112999392877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014060890005112014, "count": 10, "is_parallel": true, "self": 0.0014060890005112014 } } }, "UnityEnvironment.step": { "total": 0.10955535400012195, "count": 1, "is_parallel": true, "self": 0.0006606980000469775, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003818860000137647, "count": 1, "is_parallel": true, "self": 0.0003818860000137647 }, "communicator.exchange": { "total": 0.1064078150000114, "count": 1, "is_parallel": true, "self": 0.1064078150000114 }, "steps_from_proto": { "total": 0.002104955000049813, "count": 1, "is_parallel": true, "self": 0.00034090100029970927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017640539997501037, "count": 10, "is_parallel": true, "self": 0.0017640539997501037 } } } } } } }, "UnityEnvironment.step": { "total": 240.19872323601157, "count": 18203, "is_parallel": true, "self": 10.317054074015914, "children": { "UnityEnvironment._generate_step_input": { "total": 5.189776331006669, "count": 18203, "is_parallel": true, "self": 5.189776331006669 }, "communicator.exchange": { "total": 190.22825073398985, "count": 18203, "is_parallel": true, "self": 190.22825073398985 }, "steps_from_proto": { "total": 34.46364209699914, "count": 18203, "is_parallel": true, "self": 6.151393560937777, "children": { "_process_rank_one_or_two_observation": { "total": 28.31224853606136, "count": 182030, "is_parallel": true, "self": 28.31224853606136 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013514199986275344, "count": 1, "self": 0.00013514199986275344, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.28490344794886, "count": 441137, "is_parallel": true, "self": 9.32674061697503, "children": { "process_trajectory": { "total": 246.04121923697403, "count": 441137, "is_parallel": true, "self": 244.94292470797382, "children": { "RLTrainer._checkpoint": { "total": 1.0982945290002135, "count": 4, "is_parallel": true, "self": 1.0982945290002135 } } }, "_update_policy": { "total": 191.9169435939998, "count": 90, "is_parallel": true, "self": 73.100012380002, "children": { "TorchPPOOptimizer.update": { "total": 118.8169312139978, "count": 4587, "is_parallel": true, "self": 118.8169312139978 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14054220399998485, "count": 1, "self": 0.0009222700000464101, "children": { "RLTrainer._checkpoint": { "total": 0.13961993399993844, "count": 1, "self": 0.13961993399993844 } } } } } } }