{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.953028678894043, "min": 0.9463495016098022, "max": 2.8695690631866455, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9099.517578125, "min": 9099.517578125, "max": 29387.2578125, "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": 12.991911888122559, "min": 0.3302571773529053, "max": 12.991911888122559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.4228515625, "min": 64.06989288330078, "max": 2641.6826171875, "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.Losses.PolicyLoss.mean": { "value": 0.061620344061552985, "min": 0.06128053698743244, "max": 0.07512927636408302, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24648137624621194, "min": 0.24512214794972975, "max": 0.3756463818204151, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17798291249018092, "min": 0.12957780385691237, "max": 0.29381034385924243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7119316499607237, "min": 0.5183112154276495, "max": 1.4690517192962123, "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.CumulativeReward.mean": { "value": 25.204545454545453, "min": 3.4545454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 152.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 3.4545454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 152.0, "max": 1387.0, "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": "1710345467", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710345926" }, "total": 458.6838705120001, "count": 1, "self": 0.5911024380000072, "children": { "run_training.setup": { "total": 0.058200680000027205, "count": 1, "self": 0.058200680000027205 }, "TrainerController.start_learning": { "total": 458.0345673940001, "count": 1, "self": 0.5820838339955117, "children": { "TrainerController._reset_env": { "total": 3.3859625090001373, "count": 1, "self": 3.3859625090001373 }, "TrainerController.advance": { "total": 453.97178878100453, "count": 18199, "self": 0.2924862490024225, "children": { "env_step": { "total": 453.6793025320021, "count": 18199, "self": 291.49557029300945, "children": { "SubprocessEnvManager._take_step": { "total": 161.87897797299524, "count": 18199, "self": 1.4963444159752726, "children": { "TorchPolicy.evaluate": { "total": 160.38263355701997, "count": 18199, "self": 160.38263355701997 } } }, "workers": { "total": 0.30475426599741695, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 456.83947160799084, "count": 18199, "is_parallel": true, "self": 227.9819169839766, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00742785600004936, "count": 1, "is_parallel": true, "self": 0.005842812999617308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015850430004320515, "count": 10, "is_parallel": true, "self": 0.0015850430004320515 } } }, "UnityEnvironment.step": { "total": 0.03634975999989365, "count": 1, "is_parallel": true, "self": 0.0006623199999467033, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004084659999534779, "count": 1, "is_parallel": true, "self": 0.0004084659999534779 }, "communicator.exchange": { "total": 0.03327157200010333, "count": 1, "is_parallel": true, "self": 0.03327157200010333 }, "steps_from_proto": { "total": 0.002007401999890135, "count": 1, "is_parallel": true, "self": 0.0003711259996634908, "children": { "_process_rank_one_or_two_observation": { "total": 0.001636276000226644, "count": 10, "is_parallel": true, "self": 0.001636276000226644 } } } } } } }, "UnityEnvironment.step": { "total": 228.85755462401426, "count": 18198, "is_parallel": true, "self": 10.805953561013212, "children": { "UnityEnvironment._generate_step_input": { "total": 5.535650070995871, "count": 18198, "is_parallel": true, "self": 5.535650070995871 }, "communicator.exchange": { "total": 178.03657615198404, "count": 18198, "is_parallel": true, "self": 178.03657615198404 }, "steps_from_proto": { "total": 34.47937484002114, "count": 18198, "is_parallel": true, "self": 6.611852970014297, "children": { "_process_rank_one_or_two_observation": { "total": 27.86752187000684, "count": 181980, "is_parallel": true, "self": 27.86752187000684 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014113900010670477, "count": 1, "self": 0.00014113900010670477, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.7676914801125, "count": 707673, "is_parallel": true, "self": 15.405141419043503, "children": { "process_trajectory": { "total": 247.1670313350694, "count": 707673, "is_parallel": true, "self": 246.64389623206944, "children": { "RLTrainer._checkpoint": { "total": 0.5231351029999587, "count": 4, "is_parallel": true, "self": 0.5231351029999587 } } }, "_update_policy": { "total": 185.1955187259996, "count": 90, "is_parallel": true, "self": 51.5469574729982, "children": { "TorchPPOOptimizer.update": { "total": 133.6485612530014, "count": 4587, "is_parallel": true, "self": 133.6485612530014 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09459113099978822, "count": 1, "self": 0.001100360999998884, "children": { "RLTrainer._checkpoint": { "total": 0.09349076999978934, "count": 1, "self": 0.09349076999978934 } } } } } } }