{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9859097003936768, "min": 0.9769507050514221, "max": 2.8691153526306152, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9402.62109375, "min": 9402.62109375, "max": 29382.609375, "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": 12.26780891418457, "min": 0.3671302795410156, "max": 12.26780891418457, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2392.22265625, "min": 71.22327423095703, "max": 2495.2119140625, "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": 0.0627178876913568, "min": 0.06161428635081679, "max": 0.07108331204097554, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2508715507654272, "min": 0.24645714540326716, "max": 0.35377462564022555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18653301259174065, "min": 0.11701348444159307, "max": 0.27385440416195816, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7461320503669626, "min": 0.4680539377663723, "max": 1.3692720208097908, "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": 24.477272727272727, "min": 3.477272727272727, "max": 24.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1077.0, "min": 153.0, "max": 1315.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.477272727272727, "min": 3.477272727272727, "max": 24.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1077.0, "min": 153.0, "max": 1315.0, "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": "1706660767", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706661206" }, "total": 439.50978971899997, "count": 1, "self": 0.43987369700005274, "children": { "run_training.setup": { "total": 0.05640584200000376, "count": 1, "self": 0.05640584200000376 }, "TrainerController.start_learning": { "total": 439.0135101799999, "count": 1, "self": 0.5397714400048699, "children": { "TrainerController._reset_env": { "total": 4.173360353000021, "count": 1, "self": 4.173360353000021 }, "TrainerController.advance": { "total": 434.2063096059952, "count": 18198, "self": 0.26005279799653636, "children": { "env_step": { "total": 433.9462568079987, "count": 18198, "self": 280.63577149496825, "children": { "SubprocessEnvManager._take_step": { "total": 153.03908300501837, "count": 18198, "self": 1.4424630650102017, "children": { "TorchPolicy.evaluate": { "total": 151.59661994000817, "count": 18198, "self": 151.59661994000817 } } }, "workers": { "total": 0.2714023080120569, "count": 18198, "self": 0.0, "children": { "worker_root": { "total": 437.8559398009984, "count": 18198, "is_parallel": true, "self": 218.5532425049945, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059145809999563426, "count": 1, "is_parallel": true, "self": 0.004273795000017344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016407859999389984, "count": 10, "is_parallel": true, "self": 0.0016407859999389984 } } }, "UnityEnvironment.step": { "total": 0.03671437599996352, "count": 1, "is_parallel": true, "self": 0.00066726300008213, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039719899996271124, "count": 1, "is_parallel": true, "self": 0.00039719899996271124 }, "communicator.exchange": { "total": 0.03370990299993082, "count": 1, "is_parallel": true, "self": 0.03370990299993082 }, "steps_from_proto": { "total": 0.0019400109999878623, "count": 1, "is_parallel": true, "self": 0.00038821900011498656, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015517919998728757, "count": 10, "is_parallel": true, "self": 0.0015517919998728757 } } } } } } }, "UnityEnvironment.step": { "total": 219.30269729600388, "count": 18197, "is_parallel": true, "self": 10.698150081019094, "children": { "UnityEnvironment._generate_step_input": { "total": 5.221454561988594, "count": 18197, "is_parallel": true, "self": 5.221454561988594 }, "communicator.exchange": { "total": 169.82577812799548, "count": 18197, "is_parallel": true, "self": 169.82577812799548 }, "steps_from_proto": { "total": 33.55731452500072, "count": 18197, "is_parallel": true, "self": 6.172343511055715, "children": { "_process_rank_one_or_two_observation": { "total": 27.384971013945005, "count": 181970, "is_parallel": true, "self": 27.384971013945005 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012253299996700662, "count": 1, "self": 0.00012253299996700662, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 428.64723696993303, "count": 663275, "is_parallel": true, "self": 14.33439738687116, "children": { "process_trajectory": { "total": 236.266390782063, "count": 663275, "is_parallel": true, "self": 235.74875491206296, "children": { "RLTrainer._checkpoint": { "total": 0.5176358700000492, "count": 4, "is_parallel": true, "self": 0.5176358700000492 } } }, "_update_policy": { "total": 178.04644880099886, "count": 90, "is_parallel": true, "self": 51.48344867599735, "children": { "TorchPPOOptimizer.update": { "total": 126.56300012500151, "count": 4587, "is_parallel": true, "self": 126.56300012500151 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0939462479998383, "count": 1, "self": 0.0009842659999321768, "children": { "RLTrainer._checkpoint": { "total": 0.09296198199990613, "count": 1, "self": 0.09296198199990613 } } } } } } }