{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4039578437805176, "min": 1.4039578437805176, "max": 1.430025339126587, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71711.359375, "min": 68722.171875, "max": 76908.8125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.2504258943782, "min": 77.6251968503937, "max": 383.64885496183206, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49455.0, "min": 49084.0, "max": 50258.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999965.0, "min": 49953.0, "max": 1999965.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999965.0, "min": 49953.0, "max": 1999965.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.459073543548584, "min": 0.018553543835878372, "max": 2.520512342453003, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1443.4761962890625, "min": 2.4119606018066406, "max": 1532.5321044921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.795953742690143, "min": 1.7695171592327266, "max": 4.037188343070019, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2228.224846959114, "min": 230.03723070025444, "max": 2397.42534327507, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.795953742690143, "min": 1.7695171592327266, "max": 4.037188343070019, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2228.224846959114, "min": 230.03723070025444, "max": 2397.42534327507, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01591233358889844, "min": 0.01292848423133061, "max": 0.01996327354378688, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04773700076669533, "min": 0.02585696846266122, "max": 0.056033237107718986, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05664137527346611, "min": 0.0240341577368478, "max": 0.06413002933065097, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16992412582039834, "min": 0.0480683154736956, "max": 0.18743995763361454, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.628998790366657e-06, "min": 3.628998790366657e-06, "max": 0.0002953542015485999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.088699637109997e-05, "min": 1.088699637109997e-05, "max": 0.0008439285186904997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120963333333331, "min": 0.10120963333333331, "max": 0.19845139999999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036288999999999, "min": 0.20759540000000004, "max": 0.5813094999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.036070333333321e-05, "min": 7.036070333333321e-05, "max": 0.004922724859999998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002110821099999996, "min": 0.0002110821099999996, "max": 0.014067344050000003, "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": "1697433350", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697435937" }, "total": 2587.530253501, "count": 1, "self": 0.4820121719999406, "children": { "run_training.setup": { "total": 0.05020025199974043, "count": 1, "self": 0.05020025199974043 }, "TrainerController.start_learning": { "total": 2586.9980410770004, "count": 1, "self": 4.629699677111148, "children": { "TrainerController._reset_env": { "total": 8.257459581000148, "count": 1, "self": 8.257459581000148 }, "TrainerController.advance": { "total": 2574.0033895558895, "count": 232776, "self": 5.311940302905441, "children": { "env_step": { "total": 2021.1673107110764, "count": 232776, "self": 1680.8495176703946, "children": { "SubprocessEnvManager._take_step": { "total": 337.3006709638348, "count": 232776, "self": 17.233797288037294, "children": { "TorchPolicy.evaluate": { "total": 320.0668736757975, "count": 223024, "self": 320.0668736757975 } } }, "workers": { "total": 3.017122076847045, "count": 232776, "self": 0.0, "children": { "worker_root": { "total": 2579.231933883905, "count": 232776, "is_parallel": true, "self": 1208.8728381850083, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009049560003404622, "count": 1, "is_parallel": true, "self": 0.00028647900035139173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006184769999890705, "count": 2, "is_parallel": true, "self": 0.0006184769999890705 } } }, "UnityEnvironment.step": { "total": 0.03338995500007513, "count": 1, "is_parallel": true, "self": 0.00036137199958830024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021876300024814554, "count": 1, "is_parallel": true, "self": 0.00021876300024814554 }, "communicator.exchange": { "total": 0.031952690000252915, "count": 1, "is_parallel": true, "self": 0.031952690000252915 }, "steps_from_proto": { "total": 0.0008571299999857729, "count": 1, "is_parallel": true, "self": 0.00023660999977437314, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006205200002113997, "count": 2, "is_parallel": true, "self": 0.0006205200002113997 } } } } } } }, "UnityEnvironment.step": { "total": 1370.359095698897, "count": 232775, "is_parallel": true, "self": 43.50778489866889, "children": { "UnityEnvironment._generate_step_input": { "total": 89.83132828701946, "count": 232775, "is_parallel": true, "self": 89.83132828701946 }, "communicator.exchange": { "total": 1139.4915065390433, "count": 232775, "is_parallel": true, "self": 1139.4915065390433 }, "steps_from_proto": { "total": 97.5284759741653, "count": 232775, "is_parallel": true, "self": 35.120533864124354, "children": { "_process_rank_one_or_two_observation": { "total": 62.40794211004095, "count": 465550, "is_parallel": true, "self": 62.40794211004095 } } } } } } } } } } }, "trainer_advance": { "total": 547.5241385419076, "count": 232776, "self": 6.70940294417278, "children": { "process_trajectory": { "total": 160.78629812273266, "count": 232776, "self": 159.42117534273257, "children": { "RLTrainer._checkpoint": { "total": 1.3651227800000925, "count": 10, "self": 1.3651227800000925 } } }, "_update_policy": { "total": 380.0284374750022, "count": 97, "self": 314.9794508750174, "children": { "TorchPPOOptimizer.update": { "total": 65.0489865999848, "count": 2910, "self": 65.0489865999848 } } } } } } }, "trainer_threads": { "total": 1.3250000847619958e-06, "count": 1, "self": 1.3250000847619958e-06 }, "TrainerController._save_models": { "total": 0.1074909379995006, "count": 1, "self": 0.001953113999661582, "children": { "RLTrainer._checkpoint": { "total": 0.10553782399983902, "count": 1, "self": 0.10553782399983902 } } } } } } }