{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7907142639160156, "min": 0.7907142639160156, "max": 2.8721461296081543, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7662.81201171875, "min": 7597.68359375, "max": 29445.2421875, "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": 13.602298736572266, "min": 0.3656201660633087, "max": 13.602298736572266, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2788.47119140625, "min": 70.93031311035156, "max": 2788.47119140625, "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.Losses.PolicyLoss.mean": { "value": 0.06813456384846302, "min": 0.062279738225305324, "max": 0.07741322757050798, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3406728192423151, "min": 0.2491189529012213, "max": 0.38706613785253985, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1750225585173158, "min": 0.11491203695243479, "max": 0.2821874000278174, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.875112792586579, "min": 0.45964814780973917, "max": 1.4109370001390868, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.472727272727273, "min": 3.0, "max": 26.84090909090909, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1456.0, "min": 132.0, "max": 1468.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.472727272727273, "min": 3.0, "max": 26.84090909090909, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1456.0, "min": 132.0, "max": 1468.0, "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": "1726193437", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726194446" }, "total": 1008.8616992909999, "count": 1, "self": 0.3252798379996875, "children": { "run_training.setup": { "total": 0.05334017700010918, "count": 1, "self": 0.05334017700010918 }, "TrainerController.start_learning": { "total": 1008.4830792760001, "count": 1, "self": 1.4058142069645783, "children": { "TrainerController._reset_env": { "total": 2.298392212999943, "count": 1, "self": 2.298392212999943 }, "TrainerController.advance": { "total": 1004.6980715120355, "count": 45478, "self": 0.6259379810010159, "children": { "env_step": { "total": 1004.0721335310345, "count": 45478, "self": 657.2010364101168, "children": { "SubprocessEnvManager._take_step": { "total": 346.22715233597546, "count": 45478, "self": 3.2178929469630475, "children": { "TorchPolicy.evaluate": { "total": 343.0092593890124, "count": 45478, "self": 343.0092593890124 } } }, "workers": { "total": 0.6439447849422777, "count": 45478, "self": 0.0, "children": { "worker_root": { "total": 1006.8167697480274, "count": 45478, "is_parallel": true, "self": 519.9704444739878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022398129999601224, "count": 1, "is_parallel": true, "self": 0.0006420450004043232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015977679995557992, "count": 10, "is_parallel": true, "self": 0.0015977679995557992 } } }, "UnityEnvironment.step": { "total": 0.033606739000106245, "count": 1, "is_parallel": true, "self": 0.0006330930000331136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002681440000742441, "count": 1, "is_parallel": true, "self": 0.0002681440000742441 }, "communicator.exchange": { "total": 0.030551843000012013, "count": 1, "is_parallel": true, "self": 0.030551843000012013 }, "steps_from_proto": { "total": 0.002153658999986874, "count": 1, "is_parallel": true, "self": 0.00040735300012784137, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017463059998590325, "count": 10, "is_parallel": true, "self": 0.0017463059998590325 } } } } } } }, "UnityEnvironment.step": { "total": 486.8463252740396, "count": 45477, "is_parallel": true, "self": 18.067560677032134, "children": { "UnityEnvironment._generate_step_input": { "total": 9.653177078978388, "count": 45477, "is_parallel": true, "self": 9.653177078978388 }, "communicator.exchange": { "total": 400.2799698820493, "count": 45477, "is_parallel": true, "self": 400.2799698820493 }, "steps_from_proto": { "total": 58.845617635979806, "count": 45477, "is_parallel": true, "self": 11.631678084922669, "children": { "_process_rank_one_or_two_observation": { "total": 47.21393955105714, "count": 454770, "is_parallel": true, "self": 47.21393955105714 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001814370002648502, "count": 1, "self": 0.0001814370002648502, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1002.049253183922, "count": 722275, "is_parallel": true, "self": 9.622271071981686, "children": { "process_trajectory": { "total": 566.4279189049385, "count": 722275, "is_parallel": true, "self": 565.1601026559381, "children": { "RLTrainer._checkpoint": { "total": 1.2678162490003615, "count": 10, "is_parallel": true, "self": 1.2678162490003615 } } }, "_update_policy": { "total": 425.9990632070019, "count": 227, "is_parallel": true, "self": 94.0864709660118, "children": { "TorchPPOOptimizer.update": { "total": 331.9125922409901, "count": 11574, "is_parallel": true, "self": 331.9125922409901 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08061990699980015, "count": 1, "self": 0.0006834599998910562, "children": { "RLTrainer._checkpoint": { "total": 0.0799364469999091, "count": 1, "self": 0.0799364469999091 } } } } } } }