{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4072438478469849, "min": 1.4072438478469849, "max": 1.4305661916732788, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69517.84375, "min": 67944.390625, "max": 76364.3828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.0514950166113, "min": 78.9376, "max": 399.8015873015873, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49395.0, "min": 48756.0, "max": 50375.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999932.0, "min": 49962.0, "max": 1999932.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999932.0, "min": 49962.0, "max": 1999932.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4706006050109863, "min": 0.02737303264439106, "max": 2.504894733428955, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1487.301513671875, "min": 3.4216291904449463, "max": 1541.3978271484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8216871867742253, "min": 1.6864384317398071, "max": 3.9473415325288057, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2300.6556864380836, "min": 210.8048039674759, "max": 2390.3517414331436, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8216871867742253, "min": 1.6864384317398071, "max": 3.9473415325288057, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2300.6556864380836, "min": 210.8048039674759, "max": 2390.3517414331436, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017777266304862375, "min": 0.01271034315044138, "max": 0.019301300713878946, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03555453260972475, "min": 0.02542068630088276, "max": 0.05790390214163684, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05440299374361833, "min": 0.022962685022503135, "max": 0.06759498094518979, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10880598748723666, "min": 0.04592537004500627, "max": 0.20278494283556936, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.622048459349996e-06, "min": 4.622048459349996e-06, "max": 0.00029533185155605, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.244096918699992e-06, "min": 9.244096918699992e-06, "max": 0.0008436417187860999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10154065000000001, "min": 0.10154065000000001, "max": 0.19844394999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20308130000000002, "min": 0.20308130000000002, "max": 0.5812139000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.687843499999995e-05, "min": 8.687843499999995e-05, "max": 0.004922353104999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001737568699999999, "min": 0.0001737568699999999, "max": 0.014062573610000004, "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": "1695659598", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695662122" }, "total": 2524.825836667, "count": 1, "self": 0.44119951100037724, "children": { "run_training.setup": { "total": 0.041531860999953096, "count": 1, "self": 0.041531860999953096 }, "TrainerController.start_learning": { "total": 2524.343105295, "count": 1, "self": 4.607358351107905, "children": { "TrainerController._reset_env": { "total": 4.162296733999938, "count": 1, "self": 4.162296733999938 }, "TrainerController.advance": { "total": 2515.4492141968926, "count": 232459, "self": 5.025110792808391, "children": { "env_step": { "total": 1958.329247416164, "count": 232459, "self": 1654.0913313549734, "children": { "SubprocessEnvManager._take_step": { "total": 301.24569701602104, "count": 232459, "self": 17.42886377809532, "children": { "TorchPolicy.evaluate": { "total": 283.8168332379257, "count": 222908, "self": 283.8168332379257 } } }, "workers": { "total": 2.992219045169577, "count": 232459, "self": 0.0, "children": { "worker_root": { "total": 2516.644214177966, "count": 232459, "is_parallel": true, "self": 1164.2437734780342, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000916170999971655, "count": 1, "is_parallel": true, "self": 0.00029303099995559023, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006231400000160647, "count": 2, "is_parallel": true, "self": 0.0006231400000160647 } } }, "UnityEnvironment.step": { "total": 0.03490220499998031, "count": 1, "is_parallel": true, "self": 0.00032854899995982123, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023933199997827614, "count": 1, "is_parallel": true, "self": 0.00023933199997827614 }, "communicator.exchange": { "total": 0.03355499700001019, "count": 1, "is_parallel": true, "self": 0.03355499700001019 }, "steps_from_proto": { "total": 0.0007793270000320263, "count": 1, "is_parallel": true, "self": 0.00022807599998486694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005512510000471593, "count": 2, "is_parallel": true, "self": 0.0005512510000471593 } } } } } } }, "UnityEnvironment.step": { "total": 1352.400440699932, "count": 232458, "is_parallel": true, "self": 40.28480192990992, "children": { "UnityEnvironment._generate_step_input": { "total": 88.49965090907199, "count": 232458, "is_parallel": true, "self": 88.49965090907199 }, "communicator.exchange": { "total": 1120.6028508439035, "count": 232458, "is_parallel": true, "self": 1120.6028508439035 }, "steps_from_proto": { "total": 103.01313701704657, "count": 232458, "is_parallel": true, "self": 39.321549500006086, "children": { "_process_rank_one_or_two_observation": { "total": 63.69158751704049, "count": 464916, "is_parallel": true, "self": 63.69158751704049 } } } } } } } } } } }, "trainer_advance": { "total": 552.0948559879201, "count": 232459, "self": 6.711204897933044, "children": { "process_trajectory": { "total": 144.60524722698676, "count": 232459, "self": 143.24983020098705, "children": { "RLTrainer._checkpoint": { "total": 1.3554170259997136, "count": 10, "self": 1.3554170259997136 } } }, "_update_policy": { "total": 400.77840386300034, "count": 96, "self": 340.8263049410075, "children": { "TorchPPOOptimizer.update": { "total": 59.95209892199284, "count": 2880, "self": 59.95209892199284 } } } } } } }, "trainer_threads": { "total": 1.1429997357481625e-06, "count": 1, "self": 1.1429997357481625e-06 }, "TrainerController._save_models": { "total": 0.12423486999978195, "count": 1, "self": 0.0019274460000815452, "children": { "RLTrainer._checkpoint": { "total": 0.1223074239997004, "count": 1, "self": 0.1223074239997004 } } } } } } }