{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4080114364624023, "min": 1.4080114364624023, "max": 1.426377296447754, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71179.203125, "min": 68776.1015625, "max": 78336.484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.87049180327868, "min": 74.60968229954614, "max": 423.52542372881356, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49331.0, "min": 48920.0, "max": 49996.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999916.0, "min": 49344.0, "max": 1999916.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999916.0, "min": 49344.0, "max": 1999916.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4738709926605225, "min": 0.0796402096748352, "max": 2.5060887336730957, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1509.061279296875, "min": 9.317904472351074, "max": 1606.8653564453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.888971743720477, "min": 1.8236262404765837, "max": 4.018485540614544, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2372.272763669491, "min": 213.3642701357603, "max": 2569.9489471912384, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.888971743720477, "min": 1.8236262404765837, "max": 4.018485540614544, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2372.272763669491, "min": 213.3642701357603, "max": 2569.9489471912384, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015191227714401774, "min": 0.014726807573000163, "max": 0.01987224247030907, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04557368314320532, "min": 0.029453615146000325, "max": 0.05961672741092722, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06125342473387718, "min": 0.021122936407725015, "max": 0.0651464135075609, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18376027420163155, "min": 0.04224587281545003, "max": 0.18895976456503072, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5796488068166764e-06, "min": 3.5796488068166764e-06, "max": 0.00029531490156169994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0738946420450029e-05, "min": 1.0738946420450029e-05, "max": 0.0008439943686685498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119318333333333, "min": 0.10119318333333333, "max": 0.19843829999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30357955, "min": 0.20754614999999998, "max": 0.5813314499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.953984833333348e-05, "min": 6.953984833333348e-05, "max": 0.00492207117, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020861954500000045, "min": 0.00020861954500000045, "max": 0.014068439355000004, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718343970", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718346881" }, "total": 2910.157900354, "count": 1, "self": 0.4923350640001445, "children": { "run_training.setup": { "total": 0.0569784609999715, "count": 1, "self": 0.0569784609999715 }, "TrainerController.start_learning": { "total": 2909.608586829, "count": 1, "self": 6.033808347104241, "children": { "TrainerController._reset_env": { "total": 3.146299065999983, "count": 1, "self": 3.146299065999983 }, "TrainerController.advance": { "total": 2900.297734294896, "count": 233129, "self": 6.15685219684201, "children": { "env_step": { "total": 2314.7071264380006, "count": 233129, "self": 1907.1966982209165, "children": { "SubprocessEnvManager._take_step": { "total": 403.6178254440688, "count": 233129, "self": 20.84897359423985, "children": { "TorchPolicy.evaluate": { "total": 382.76885184982893, "count": 222922, "self": 382.76885184982893 } } }, "workers": { "total": 3.892602773015369, "count": 233129, "self": 0.0, "children": { "worker_root": { "total": 2900.418928364926, "count": 233129, "is_parallel": true, "self": 1374.9652446758682, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008700470000349014, "count": 1, "is_parallel": true, "self": 0.00022823399990556936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006418130001293321, "count": 2, "is_parallel": true, "self": 0.0006418130001293321 } } }, "UnityEnvironment.step": { "total": 0.03378454099993178, "count": 1, "is_parallel": true, "self": 0.0004632309999124118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002058480001778662, "count": 1, "is_parallel": true, "self": 0.0002058480001778662 }, "communicator.exchange": { "total": 0.03237266099995395, "count": 1, "is_parallel": true, "self": 0.03237266099995395 }, "steps_from_proto": { "total": 0.0007428009998875496, "count": 1, "is_parallel": true, "self": 0.0002116169998771511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005311840000103984, "count": 2, "is_parallel": true, "self": 0.0005311840000103984 } } } } } } }, "UnityEnvironment.step": { "total": 1525.453683689058, "count": 233128, "is_parallel": true, "self": 47.432378706158715, "children": { "UnityEnvironment._generate_step_input": { "total": 92.14297409697951, "count": 233128, "is_parallel": true, "self": 92.14297409697951 }, "communicator.exchange": { "total": 1278.0037119129838, "count": 233128, "is_parallel": true, "self": 1278.0037119129838 }, "steps_from_proto": { "total": 107.87461897293588, "count": 233128, "is_parallel": true, "self": 36.746635918763786, "children": { "_process_rank_one_or_two_observation": { "total": 71.12798305417209, "count": 466256, "is_parallel": true, "self": 71.12798305417209 } } } } } } } } } } }, "trainer_advance": { "total": 579.4337556600537, "count": 233129, "self": 8.804788761083955, "children": { "process_trajectory": { "total": 188.5040152819704, "count": 233129, "self": 186.9663096289703, "children": { "RLTrainer._checkpoint": { "total": 1.5377056530001028, "count": 10, "self": 1.5377056530001028 } } }, "_update_policy": { "total": 382.1249516169994, "count": 97, "self": 310.93431760898625, "children": { "TorchPPOOptimizer.update": { "total": 71.19063400801315, "count": 2910, "self": 71.19063400801315 } } } } } } }, "trainer_threads": { "total": 1.6949998098425567e-06, "count": 1, "self": 1.6949998098425567e-06 }, "TrainerController._save_models": { "total": 0.13074342599975353, "count": 1, "self": 0.00267736000023433, "children": { "RLTrainer._checkpoint": { "total": 0.1280660659995192, "count": 1, "self": 0.1280660659995192 } } } } } } }