{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7519572377204895, "min": 0.7519572377204895, "max": 2.8669838905334473, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7146.6015625, "min": 7146.6015625, "max": 29266.171875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.714452743530273, "min": 0.2747448980808258, "max": 11.714452743530273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2284.318359375, "min": 53.30051040649414, "max": 2374.19775390625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0688137029309491, "min": 0.061131025397081235, "max": 0.07553026660123435, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2752548117237964, "min": 0.24452410158832494, "max": 0.3725485251270584, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1805135707790945, "min": 0.13250813565522834, "max": 0.2922548410939235, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.722054283116378, "min": 0.5300325426209134, "max": 1.4612742054696175, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.34090909090909, "min": 3.409090909090909, "max": 23.34090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1027.0, "min": 150.0, "max": 1261.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.34090909090909, "min": 3.409090909090909, "max": 23.34090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1027.0, "min": 150.0, "max": 1261.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788622165", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788622779" }, "total": 614.0732186639998, "count": 1, "self": 0.6484573599993837, "children": { "run_training.setup": { "total": 0.025547870000082185, "count": 1, "self": 0.025547870000082185 }, "TrainerController.start_learning": { "total": 613.3992134340003, "count": 1, "self": 0.6716561099972296, "children": { "TrainerController._reset_env": { "total": 3.267383124000162, "count": 1, "self": 3.267383124000162 }, "TrainerController.advance": { "total": 609.384929585003, "count": 18192, "self": 0.7201473689801787, "children": { "env_step": { "total": 438.9550710470196, "count": 18192, "self": 380.9820896269923, "children": { "SubprocessEnvManager._take_step": { "total": 57.58830869699841, "count": 18192, "self": 2.109430136049923, "children": { "TorchPolicy.evaluate": { "total": 55.47887856094849, "count": 18192, "self": 55.47887856094849 } } }, "workers": { "total": 0.3846727230288707, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 609.947789947973, "count": 18192, "is_parallel": true, "self": 280.5846521969481, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004018297000129678, "count": 1, "is_parallel": true, "self": 0.0013999530003729888, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026183439997566893, "count": 10, "is_parallel": true, "self": 0.0026183439997566893 } } }, "UnityEnvironment.step": { "total": 0.05067656799997167, "count": 1, "is_parallel": true, "self": 0.0007015669998509111, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004530890000751242, "count": 1, "is_parallel": true, "self": 0.0004530890000751242 }, "communicator.exchange": { "total": 0.046940121000034196, "count": 1, "is_parallel": true, "self": 0.046940121000034196 }, "steps_from_proto": { "total": 0.0025817910000114352, "count": 1, "is_parallel": true, "self": 0.0005621379996227915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020196530003886437, "count": 10, "is_parallel": true, "self": 0.0020196530003886437 } } } } } } }, "UnityEnvironment.step": { "total": 329.36313775102485, "count": 18191, "is_parallel": true, "self": 14.248947150019376, "children": { "UnityEnvironment._generate_step_input": { "total": 7.685409576959955, "count": 18191, "is_parallel": true, "self": 7.685409576959955 }, "communicator.exchange": { "total": 256.1507111789997, "count": 18191, "is_parallel": true, "self": 256.1507111789997 }, "steps_from_proto": { "total": 51.27806984504582, "count": 18191, "is_parallel": true, "self": 9.169200112966337, "children": { "_process_rank_one_or_two_observation": { "total": 42.108869732079484, "count": 181910, "is_parallel": true, "self": 42.108869732079484 } } } } } } } } } } }, "trainer_advance": { "total": 169.70971116900319, "count": 18192, "self": 0.85882243900096, "children": { "process_trajectory": { "total": 30.134976174002986, "count": 18192, "self": 29.748762183002782, "children": { "RLTrainer._checkpoint": { "total": 0.38621399100020426, "count": 4, "self": 0.38621399100020426 } } }, "_update_policy": { "total": 138.71591255599924, "count": 90, "self": 50.52282776898619, "children": { "TorchPPOOptimizer.update": { "total": 88.19308478701305, "count": 4587, "self": 88.19308478701305 } } } } } } }, "trainer_threads": { "total": 1.1460001587693114e-06, "count": 1, "self": 1.1460001587693114e-06 }, "TrainerController._save_models": { "total": 0.07524346899981538, "count": 1, "self": 0.0012593619999279326, "children": { "RLTrainer._checkpoint": { "total": 0.07398410699988744, "count": 1, "self": 0.07398410699988744 } } } } } } }