{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40358304977417, "min": 1.40358304977417, "max": 1.4275671243667603, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70127.21875, "min": 68335.984375, "max": 78709.6484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.72280701754386, "min": 86.13763066202091, "max": 403.61290322580646, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49432.0, "min": 49145.0, "max": 50191.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49846.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49846.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4335739612579346, "min": 0.22307144105434418, "max": 2.4650888442993164, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1387.13720703125, "min": 27.437788009643555, "max": 1402.2105712890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.757414835482313, "min": 1.961903014561025, "max": 4.01754723632403, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2141.7264562249184, "min": 241.3140707910061, "max": 2170.72803992033, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.757414835482313, "min": 1.961903014561025, "max": 4.01754723632403, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2141.7264562249184, "min": 241.3140707910061, "max": 2170.72803992033, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01665457813974677, "min": 0.012483907513402906, "max": 0.019459624055889434, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049963734419240305, "min": 0.026929914254287722, "max": 0.05522323688104128, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057640505623486306, "min": 0.020540864175806445, "max": 0.05897592157125473, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17292151687045892, "min": 0.04108172835161289, "max": 0.1769277647137642, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.365598878166666e-06, "min": 3.365598878166666e-06, "max": 0.00029536200154599995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0096796634499998e-05, "min": 1.0096796634499998e-05, "max": 0.0008442195185935, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112183333333336, "min": 0.10112183333333336, "max": 0.19845399999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30336550000000007, "min": 0.20738224999999996, "max": 0.5814065, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.597948333333333e-05, "min": 6.597948333333333e-05, "max": 0.0049228546, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019793845, "min": 0.00019793845, "max": 0.014072184350000001, "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": "1672941032", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1672943424" }, "total": 2392.057608997, "count": 1, "self": 0.3839657050002643, "children": { "run_training.setup": { "total": 0.10879844000010053, "count": 1, "self": 0.10879844000010053 }, "TrainerController.start_learning": { "total": 2391.5648448519996, "count": 1, "self": 4.132852988955619, "children": { "TrainerController._reset_env": { "total": 7.121132347999946, "count": 1, "self": 7.121132347999946 }, "TrainerController.advance": { "total": 2380.1910289580437, "count": 232047, "self": 4.508717935274035, "children": { "env_step": { "total": 1887.8281167409466, "count": 232047, "self": 1587.6063242030223, "children": { "SubprocessEnvManager._take_step": { "total": 297.3802512819584, "count": 232047, "self": 15.668862674966704, "children": { "TorchPolicy.evaluate": { "total": 281.7113886069917, "count": 222999, "self": 69.04030021601397, "children": { "TorchPolicy.sample_actions": { "total": 212.67108839097773, "count": 222999, "self": 212.67108839097773 } } } } }, "workers": { "total": 2.8415412559659217, "count": 232047, "self": 0.0, "children": { "worker_root": { "total": 2382.97799883905, "count": 232047, "is_parallel": true, "self": 1077.2487858889788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017335040001853486, "count": 1, "is_parallel": true, "self": 0.0003330210001877276, "children": { "_process_rank_one_or_two_observation": { "total": 0.001400482999997621, "count": 2, "is_parallel": true, "self": 0.001400482999997621 } } }, "UnityEnvironment.step": { "total": 0.03243245599992406, "count": 1, "is_parallel": true, "self": 0.0003398439998818503, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022082400005274394, "count": 1, "is_parallel": true, "self": 0.00022082400005274394 }, "communicator.exchange": { "total": 0.03100059100006547, "count": 1, "is_parallel": true, "self": 0.03100059100006547 }, "steps_from_proto": { "total": 0.0008711969999239955, "count": 1, "is_parallel": true, "self": 0.000303121000115425, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005680759998085705, "count": 2, "is_parallel": true, "self": 0.0005680759998085705 } } } } } } }, "UnityEnvironment.step": { "total": 1305.7292129500713, "count": 232046, "is_parallel": true, "self": 36.859462708071305, "children": { "UnityEnvironment._generate_step_input": { "total": 85.28554225793118, "count": 232046, "is_parallel": true, "self": 85.28554225793118 }, "communicator.exchange": { "total": 1082.8776438109326, "count": 232046, "is_parallel": true, "self": 1082.8776438109326 }, "steps_from_proto": { "total": 100.70656417313626, "count": 232046, "is_parallel": true, "self": 44.04921635012943, "children": { "_process_rank_one_or_two_observation": { "total": 56.65734782300683, "count": 464092, "is_parallel": true, "self": 56.65734782300683 } } } } } } } } } } }, "trainer_advance": { "total": 487.8541942818233, "count": 232047, "self": 6.335036595768997, "children": { "process_trajectory": { "total": 157.35000511205385, "count": 232047, "self": 156.140599760055, "children": { "RLTrainer._checkpoint": { "total": 1.2094053519988393, "count": 10, "self": 1.2094053519988393 } } }, "_update_policy": { "total": 324.16915257400046, "count": 97, "self": 270.6241105770057, "children": { "TorchPPOOptimizer.update": { "total": 53.54504199699477, "count": 2910, "self": 53.54504199699477 } } } } } } }, "trainer_threads": { "total": 1.027000052999938e-06, "count": 1, "self": 1.027000052999938e-06 }, "TrainerController._save_models": { "total": 0.11982953000006091, "count": 1, "self": 0.001989337999930285, "children": { "RLTrainer._checkpoint": { "total": 0.11784019200013063, "count": 1, "self": 0.11784019200013063 } } } } } } }