{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3992754220962524, "min": 1.3992754220962524, "max": 1.4226139783859253, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71234.3125, "min": 67608.96875, "max": 78485.8828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.080204778157, "min": 79.86407766990291, "max": 379.95454545454544, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49857.0, "min": 49040.0, "max": 50154.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999772.0, "min": 49586.0, "max": 1999772.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999772.0, "min": 49586.0, "max": 1999772.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.429859161376953, "min": 0.005918058566749096, "max": 2.5066163539886475, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1423.8974609375, "min": 0.7752656936645508, "max": 1522.224365234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7579705776208088, "min": 1.7261705382634664, "max": 3.9528932315962657, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2202.170758485794, "min": 226.12834051251411, "max": 2362.9064193964005, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7579705776208088, "min": 1.7261705382634664, "max": 3.9528932315962657, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2202.170758485794, "min": 226.12834051251411, "max": 2362.9064193964005, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016666996888428307, "min": 0.014074512087770724, "max": 0.019543459454628948, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05000099066528492, "min": 0.029360867010351892, "max": 0.05684906305359619, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053139806662996614, "min": 0.024828965651492278, "max": 0.060315325607856116, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15941941998898984, "min": 0.049657931302984556, "max": 0.17903639910121757, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6433987855666602e-06, "min": 3.6433987855666602e-06, "max": 0.0002953527015491001, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.093019635669998e-05, "min": 1.093019635669998e-05, "max": 0.0008442798185733998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121443333333335, "min": 0.10121443333333335, "max": 0.19845089999999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30364330000000006, "min": 0.20756190000000002, "max": 0.5814265999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.060022333333324e-05, "min": 7.060022333333324e-05, "max": 0.004922699910000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021180066999999973, "min": 0.00021180066999999973, "max": 0.014073187339999998, "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": "1672693157", "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": "1672695538" }, "total": 2380.4885732169996, "count": 1, "self": 0.3888938829995823, "children": { "run_training.setup": { "total": 0.11154564100002062, "count": 1, "self": 0.11154564100002062 }, "TrainerController.start_learning": { "total": 2379.9881336930002, "count": 1, "self": 4.271297382997545, "children": { "TrainerController._reset_env": { "total": 7.6753644209999266, "count": 1, "self": 7.6753644209999266 }, "TrainerController.advance": { "total": 2367.9159381720033, "count": 232818, "self": 4.327540198052247, "children": { "env_step": { "total": 1875.3511557710146, "count": 232818, "self": 1573.1488223400006, "children": { "SubprocessEnvManager._take_step": { "total": 299.4434823340488, "count": 232818, "self": 15.511486690052152, "children": { "TorchPolicy.evaluate": { "total": 283.93199564399663, "count": 223039, "self": 69.94427837103228, "children": { "TorchPolicy.sample_actions": { "total": 213.98771727296435, "count": 223039, "self": 213.98771727296435 } } } } }, "workers": { "total": 2.7588510969653726, "count": 232818, "self": 0.0, "children": { "worker_root": { "total": 2371.630582670061, "count": 232818, "is_parallel": true, "self": 1077.2432030539032, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002254163999964476, "count": 1, "is_parallel": true, "self": 0.0003312090000235912, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019229549999408846, "count": 2, "is_parallel": true, "self": 0.0019229549999408846 } } }, "UnityEnvironment.step": { "total": 0.029465662000006887, "count": 1, "is_parallel": true, "self": 0.0003162579999980153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019091799993020686, "count": 1, "is_parallel": true, "self": 0.00019091799993020686 }, "communicator.exchange": { "total": 0.028202404000012393, "count": 1, "is_parallel": true, "self": 0.028202404000012393 }, "steps_from_proto": { "total": 0.0007560820000662716, "count": 1, "is_parallel": true, "self": 0.00025802900006510754, "children": { "_process_rank_one_or_two_observation": { "total": 0.000498053000001164, "count": 2, "is_parallel": true, "self": 0.000498053000001164 } } } } } } }, "UnityEnvironment.step": { "total": 1294.3873796161577, "count": 232817, "is_parallel": true, "self": 36.1119800023082, "children": { "UnityEnvironment._generate_step_input": { "total": 85.42845444498005, "count": 232817, "is_parallel": true, "self": 85.42845444498005 }, "communicator.exchange": { "total": 1073.1969761208657, "count": 232817, "is_parallel": true, "self": 1073.1969761208657 }, "steps_from_proto": { "total": 99.64996904800353, "count": 232817, "is_parallel": true, "self": 43.26156298906699, "children": { "_process_rank_one_or_two_observation": { "total": 56.38840605893654, "count": 465634, "is_parallel": true, "self": 56.38840605893654 } } } } } } } } } } }, "trainer_advance": { "total": 488.2372422029365, "count": 232818, "self": 6.2543722870658485, "children": { "process_trajectory": { "total": 162.8182278938698, "count": 232818, "self": 161.60791244986967, "children": { "RLTrainer._checkpoint": { "total": 1.2103154440001163, "count": 10, "self": 1.2103154440001163 } } }, "_update_policy": { "total": 319.16464202200086, "count": 97, "self": 265.77658504899796, "children": { "TorchPPOOptimizer.update": { "total": 53.388056973002904, "count": 2910, "self": 53.388056973002904 } } } } } } }, "trainer_threads": { "total": 1.189999693451682e-06, "count": 1, "self": 1.189999693451682e-06 }, "TrainerController._save_models": { "total": 0.1255325269999048, "count": 1, "self": 0.0022850399996059423, "children": { "RLTrainer._checkpoint": { "total": 0.12324748700029886, "count": 1, "self": 0.12324748700029886 } } } } } } }