{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7032978534698486, "min": 0.6861177682876587, "max": 2.8395602703094482, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6746.033203125, "min": 6695.162109375, "max": 28986.23046875, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.289865493774414, "min": 0.3287927806377411, "max": 14.304574966430664, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2929.42236328125, "min": 63.785797119140625, "max": 2929.42236328125, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04863436290470417, "min": 0.04113712745747762, "max": 0.055625689928516894, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24317181452352088, "min": 0.16458434821023124, "max": 0.2781284496425845, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15544735391934714, "min": 0.1274896142228196, "max": 0.31084254710003734, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7772367695967357, "min": 0.5099584568912784, "max": 1.5178516370554764, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000023e-06, "min": 3.0528989824000023e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.526449491200001e-05, "min": 1.526449491200001e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1010176, "min": 0.1010176, "max": 0.19891760000000003, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.505088, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.077824000000003e-05, "min": 6.077824000000003e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00030389120000000016, "min": 0.00030389120000000016, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.4, "min": 3.3636363636363638, "max": 28.4, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1562.0, "min": 148.0, "max": 1562.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.4, "min": 3.3636363636363638, "max": 28.4, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1562.0, "min": 148.0, "max": 1562.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1777729313", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1777730494" }, "total": 1181.368916793, "count": 1, "self": 0.43156197500002236, "children": { "run_training.setup": { "total": 0.028030607000118835, "count": 1, "self": 0.028030607000118835 }, "TrainerController.start_learning": { "total": 1180.9093242109998, "count": 1, "self": 1.0093438759895434, "children": { "TrainerController._reset_env": { "total": 3.3812274229999275, "count": 1, "self": 3.3812274229999275 }, "TrainerController.advance": { "total": 1176.4040868240104, "count": 45464, "self": 1.0230051929884212, "children": { "env_step": { "total": 883.5455014400122, "count": 45464, "self": 667.7893890009657, "children": { "SubprocessEnvManager._take_step": { "total": 215.13978082403196, "count": 45464, "self": 3.3869330840586827, "children": { "TorchPolicy.evaluate": { "total": 211.75284773997328, "count": 45464, "self": 211.75284773997328 } } }, "workers": { "total": 0.6163316150145874, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1176.4576041149796, "count": 45464, "is_parallel": true, "self": 590.377084847948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027114970000639005, "count": 1, "is_parallel": true, "self": 0.000850822000302287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018606749997616134, "count": 10, "is_parallel": true, "self": 0.0018606749997616134 } } }, "UnityEnvironment.step": { "total": 0.07367305100001431, "count": 1, "is_parallel": true, "self": 0.0006398590001026605, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037883799996052403, "count": 1, "is_parallel": true, "self": 0.00037883799996052403 }, "communicator.exchange": { "total": 0.0694678570000633, "count": 1, "is_parallel": true, "self": 0.0694678570000633 }, "steps_from_proto": { "total": 0.0031864969998878223, "count": 1, "is_parallel": true, "self": 0.0004000019996510673, "children": { "_process_rank_one_or_two_observation": { "total": 0.002786495000236755, "count": 10, "is_parallel": true, "self": 0.002786495000236755 } } } } } } }, "UnityEnvironment.step": { "total": 586.0805192670316, "count": 45463, "is_parallel": true, "self": 27.059333113960065, "children": { "UnityEnvironment._generate_step_input": { "total": 14.633036592026883, "count": 45463, "is_parallel": true, "self": 14.633036592026883 }, "communicator.exchange": { "total": 445.58834218103834, "count": 45463, "is_parallel": true, "self": 445.58834218103834 }, "steps_from_proto": { "total": 98.79980738000631, "count": 45463, "is_parallel": true, "self": 17.258371522254038, "children": { "_process_rank_one_or_two_observation": { "total": 81.54143585775228, "count": 454630, "is_parallel": true, "self": 81.54143585775228 } } } } } } } } } } }, "trainer_advance": { "total": 291.83558019100974, "count": 45464, "self": 1.2231956810476277, "children": { "process_trajectory": { "total": 112.40375217396036, "count": 45464, "self": 110.81153524796014, "children": { "RLTrainer._checkpoint": { "total": 1.5922169260002192, "count": 10, "self": 1.5922169260002192 } } }, "_update_policy": { "total": 178.20863233600176, "count": 227, "self": 97.77838447499812, "children": { "TorchPPOOptimizer.update": { "total": 80.43024786100364, "count": 5448, "self": 80.43024786100364 } } } } } } }, "trainer_threads": { "total": 1.785199992809794e-05, "count": 1, "self": 1.785199992809794e-05 }, "TrainerController._save_models": { "total": 0.11464823599999363, "count": 1, "self": 0.0008794159998615214, "children": { "RLTrainer._checkpoint": { "total": 0.11376882000013211, "count": 1, "self": 0.11376882000013211 } } } } } } }