{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054663181304932, "min": 1.4054663181304932, "max": 1.4303135871887207, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70477.109375, "min": 68467.1640625, "max": 78060.3046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 67.11836734693877, "min": 67.11836734693877, "max": 390.5390625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49332.0, "min": 49184.0, "max": 49990.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999958.0, "min": 49649.0, "max": 1999958.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999958.0, "min": 49649.0, "max": 1999958.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4855728149414062, "min": 0.07142408937215805, "max": 2.5505776405334473, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1824.410400390625, "min": 9.0708589553833, "max": 1825.003662109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.869849533167457, "min": 1.8116912349002567, "max": 4.076990348170172, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2840.4695573449135, "min": 230.0847868323326, "max": 2901.2514068484306, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.869849533167457, "min": 1.8116912349002567, "max": 4.076990348170172, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2840.4695573449135, "min": 230.0847868323326, "max": 2901.2514068484306, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016089913363167497, "min": 0.014259655943412023, "max": 0.021197360063282152, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048269740089502494, "min": 0.028519311886824047, "max": 0.061160277368132177, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05751123527685801, "min": 0.023282089736312628, "max": 0.06395826445271571, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17253370583057404, "min": 0.046564179472625256, "max": 0.18396461978554726, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.904048698683335e-06, "min": 3.904048698683335e-06, "max": 0.000295346026551325, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1712146096050004e-05, "min": 1.1712146096050004e-05, "max": 0.0008437306687564502, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130131666666668, "min": 0.10130131666666668, "max": 0.19844867499999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30390395000000003, "min": 0.20772535000000003, "max": 0.5812435500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.493570166666669e-05, "min": 7.493570166666669e-05, "max": 0.004922588882500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022480710500000006, "min": 0.00022480710500000006, "max": 0.014064053145000002, "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": "1698825276", "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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698827826" }, "total": 2550.706174426, "count": 1, "self": 0.6037578340001346, "children": { "run_training.setup": { "total": 0.06680512499997349, "count": 1, "self": 0.06680512499997349 }, "TrainerController.start_learning": { "total": 2550.035611467, "count": 1, "self": 4.709494121883381, "children": { "TrainerController._reset_env": { "total": 8.696925730999965, "count": 1, "self": 8.696925730999965 }, "TrainerController.advance": { "total": 2536.532446987117, "count": 233512, "self": 5.003970455104991, "children": { "env_step": { "total": 2005.7253101970066, "count": 233512, "self": 1650.3960309280142, "children": { "SubprocessEnvManager._take_step": { "total": 352.26948193497356, "count": 233512, "self": 17.38224887902311, "children": { "TorchPolicy.evaluate": { "total": 334.88723305595045, "count": 222894, "self": 334.88723305595045 } } }, "workers": { "total": 3.0597973340187536, "count": 233512, "self": 0.0, "children": { "worker_root": { "total": 2542.1185072970284, "count": 233512, "is_parallel": true, "self": 1203.3306469430572, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010929149999583387, "count": 1, "is_parallel": true, "self": 0.00034117300003799755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007517419999203412, "count": 2, "is_parallel": true, "self": 0.0007517419999203412 } } }, "UnityEnvironment.step": { "total": 0.030289818999904128, "count": 1, "is_parallel": true, "self": 0.0002950479999981326, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002123040000014953, "count": 1, "is_parallel": true, "self": 0.0002123040000014953 }, "communicator.exchange": { "total": 0.029072705999965365, "count": 1, "is_parallel": true, "self": 0.029072705999965365 }, "steps_from_proto": { "total": 0.0007097609999391352, "count": 1, "is_parallel": true, "self": 0.00021601599996756704, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004937449999715682, "count": 2, "is_parallel": true, "self": 0.0004937449999715682 } } } } } } }, "UnityEnvironment.step": { "total": 1338.7878603539712, "count": 233511, "is_parallel": true, "self": 41.809913204758686, "children": { "UnityEnvironment._generate_step_input": { "total": 91.07374422903467, "count": 233511, "is_parallel": true, "self": 91.07374422903467 }, "communicator.exchange": { "total": 1110.9911886091331, "count": 233511, "is_parallel": true, "self": 1110.9911886091331 }, "steps_from_proto": { "total": 94.91301431104466, "count": 233511, "is_parallel": true, "self": 36.08335567304982, "children": { "_process_rank_one_or_two_observation": { "total": 58.82965863799484, "count": 467022, "is_parallel": true, "self": 58.82965863799484 } } } } } } } } } } }, "trainer_advance": { "total": 525.8031663350054, "count": 233512, "self": 7.024625934827554, "children": { "process_trajectory": { "total": 167.9041257151763, "count": 233512, "self": 166.74447558217616, "children": { "RLTrainer._checkpoint": { "total": 1.1596501330001274, "count": 10, "self": 1.1596501330001274 } } }, "_update_policy": { "total": 350.8744146850015, "count": 97, "self": 287.64074972500407, "children": { "TorchPPOOptimizer.update": { "total": 63.23366495999744, "count": 2910, "self": 63.23366495999744 } } } } } } }, "trainer_threads": { "total": 1.0799999472510535e-06, "count": 1, "self": 1.0799999472510535e-06 }, "TrainerController._save_models": { "total": 0.09674354699973264, "count": 1, "self": 0.0018846409998332092, "children": { "RLTrainer._checkpoint": { "total": 0.09485890599989943, "count": 1, "self": 0.09485890599989943 } } } } } } }