{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7947409749031067, "min": 0.7947409749031067, "max": 2.8620705604553223, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8077.7470703125, "min": 7707.5380859375, "max": 29373.4296875, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.424864768981934, "min": 0.30811837315559387, "max": 13.424864768981934, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2617.8486328125, "min": 59.77496337890625, "max": 2741.96337890625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06454560666472889, "min": 0.06074054387920792, "max": 0.074167566525327, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25818242665891555, "min": 0.24421002876524833, "max": 0.370837832626635, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20385289732732026, "min": 0.14457374546270563, "max": 0.27931074681235296, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.815411589309281, "min": 0.5782949818508225, "max": 1.3713825865119111, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.5940987029999965e-06, "min": 2.5940987029999965e-06, "max": 0.000197294001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0376394811999986e-05, "min": 1.0376394811999986e-05, "max": 0.00096172001914, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101297, "min": 0.101297, "max": 0.19864700000000002, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.405188, "min": 0.405188, "max": 0.98086, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999992e-05, "min": 7.472029999999992e-05, "max": 0.004932485299999999, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999966, "min": 0.00029888119999999966, "max": 0.024044914, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.431818181818183, "min": 3.8181818181818183, "max": 26.431818181818183, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1163.0, "min": 168.0, "max": 1449.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.431818181818183, "min": 3.8181818181818183, "max": 26.431818181818183, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1163.0, "min": 168.0, "max": 1449.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723831439", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723832665" }, "total": 1225.6518520080003, "count": 1, "self": 0.5952232290005668, "children": { "run_training.setup": { "total": 0.09091497700001128, "count": 1, "self": 0.09091497700001128 }, "TrainerController.start_learning": { "total": 1224.9657138019998, "count": 1, "self": 1.6150285529806752, "children": { "TrainerController._reset_env": { "total": 4.874541996000062, "count": 1, "self": 4.874541996000062 }, "TrainerController.advance": { "total": 1218.3798316620187, "count": 36400, "self": 0.8544763460145077, "children": { "env_step": { "total": 1217.5253553160042, "count": 36400, "self": 939.4780412090043, "children": { "SubprocessEnvManager._take_step": { "total": 277.20442027199715, "count": 36400, "self": 4.874734447951596, "children": { "TorchPolicy.evaluate": { "total": 272.32968582404555, "count": 36400, "self": 272.32968582404555 } } }, "workers": { "total": 0.8428938350026556, "count": 36400, "self": 0.0, "children": { "worker_root": { "total": 1220.97974874999, "count": 36400, "is_parallel": true, "self": 588.2428607999832, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008710908000011841, "count": 1, "is_parallel": true, "self": 0.00565206499982196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030588430001898814, "count": 10, "is_parallel": true, "self": 0.0030588430001898814 } } }, "UnityEnvironment.step": { "total": 0.04635482699995919, "count": 1, "is_parallel": true, "self": 0.0008227309999710997, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004527680000592227, "count": 1, "is_parallel": true, "self": 0.0004527680000592227 }, "communicator.exchange": { "total": 0.04247283899997001, "count": 1, "is_parallel": true, "self": 0.04247283899997001 }, "steps_from_proto": { "total": 0.002606488999958856, "count": 1, "is_parallel": true, "self": 0.0004839759997139481, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021225130002449077, "count": 10, "is_parallel": true, "self": 0.0021225130002449077 } } } } } } }, "UnityEnvironment.step": { "total": 632.7368879500068, "count": 36399, "is_parallel": true, "self": 30.229353984987824, "children": { "UnityEnvironment._generate_step_input": { "total": 15.235371787013605, "count": 36399, "is_parallel": true, "self": 15.235371787013605 }, "communicator.exchange": { "total": 497.27862538700526, "count": 36399, "is_parallel": true, "self": 497.27862538700526 }, "steps_from_proto": { "total": 89.99353679100011, "count": 36399, "is_parallel": true, "self": 17.680752999021934, "children": { "_process_rank_one_or_two_observation": { "total": 72.31278379197818, "count": 363990, "is_parallel": true, "self": 72.31278379197818 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00042596899993441184, "count": 1, "self": 0.00042596899993441184, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1204.2508206179234, "count": 1564804, "is_parallel": true, "self": 37.052642806129825, "children": { "process_trajectory": { "total": 638.6995964737937, "count": 1564804, "is_parallel": true, "self": 636.6551229837937, "children": { "RLTrainer._checkpoint": { "total": 2.044473489999973, "count": 8, "is_parallel": true, "self": 2.044473489999973 } } }, "_update_policy": { "total": 528.4985813379999, "count": 181, "is_parallel": true, "self": 148.3633733199904, "children": { "TorchPPOOptimizer.update": { "total": 380.1352080180095, "count": 9228, "is_parallel": true, "self": 380.1352080180095 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09588562200042361, "count": 1, "self": 0.0013083770004413964, "children": { "RLTrainer._checkpoint": { "total": 0.09457724499998221, "count": 1, "self": 0.09457724499998221 } } } } } } }