{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4047821760177612, "min": 1.4047821760177612, "max": 1.4287188053131104, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70663.3515625, "min": 68499.1328125, "max": 77890.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.18849206349206, "min": 95.36538461538461, "max": 397.43650793650795, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49487.0, "min": 48942.0, "max": 50082.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999895.0, "min": 49691.0, "max": 1999895.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999895.0, "min": 49691.0, "max": 1999895.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.438795804977417, "min": 0.01583796739578247, "max": 2.438795804977417, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1229.153076171875, "min": 1.979745864868164, "max": 1229.153076171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8547631336583033, "min": 1.8123050901889801, "max": 3.8547631336583033, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1942.8006193637848, "min": 226.5381362736225, "max": 1942.8006193637848, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8547631336583033, "min": 1.8123050901889801, "max": 3.8547631336583033, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1942.8006193637848, "min": 226.5381362736225, "max": 1942.8006193637848, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016682821924526556, "min": 0.013776541255841341, "max": 0.020020651710607733, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050048465773579666, "min": 0.027553082511682682, "max": 0.0595539874843477, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051224497664305896, "min": 0.02234196318313479, "max": 0.05679349025918378, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1536734929929177, "min": 0.04468392636626958, "max": 0.17038047077755133, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2566989144666764e-06, "min": 3.2566989144666764e-06, "max": 0.00029538877653707493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.770096743400029e-06, "min": 9.770096743400029e-06, "max": 0.000844344018552, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10108553333333335, "min": 0.10108553333333335, "max": 0.19846292500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30325660000000004, "min": 0.2073769000000001, "max": 0.5814480000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.416811333333351e-05, "min": 6.416811333333351e-05, "max": 0.0049232999575, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019250434000000054, "min": 0.00019250434000000054, "max": 0.0140742552, "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": "1685496982", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1685501488" }, "total": 4505.740060380001, "count": 1, "self": 0.5932400430001508, "children": { "run_training.setup": { "total": 0.05076498400001128, "count": 1, "self": 0.05076498400001128 }, "TrainerController.start_learning": { "total": 4505.096055353, "count": 1, "self": 8.245653819105428, "children": { "TrainerController._reset_env": { "total": 0.9425493969999934, "count": 1, "self": 0.9425493969999934 }, "TrainerController.advance": { "total": 4495.757508119895, "count": 231237, "self": 8.162557406915766, "children": { "env_step": { "total": 2803.970207228956, "count": 231237, "self": 2379.2395507761094, "children": { "SubprocessEnvManager._take_step": { "total": 419.215807607953, "count": 231237, "self": 29.01081787500914, "children": { "TorchPolicy.evaluate": { "total": 390.2049897329439, "count": 222975, "self": 390.2049897329439 } } }, "workers": { "total": 5.514848844893891, "count": 231237, "self": 0.0, "children": { "worker_root": { "total": 4490.324874471882, "count": 231237, "is_parallel": true, "self": 2588.5609830257154, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014705439999715963, "count": 1, "is_parallel": true, "self": 0.0005448279999882288, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009257159999833675, "count": 2, "is_parallel": true, "self": 0.0009257159999833675 } } }, "UnityEnvironment.step": { "total": 0.03883563800002321, "count": 1, "is_parallel": true, "self": 0.0004896060000874058, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027902900001208764, "count": 1, "is_parallel": true, "self": 0.00027902900001208764 }, "communicator.exchange": { "total": 0.037134709999918414, "count": 1, "is_parallel": true, "self": 0.037134709999918414 }, "steps_from_proto": { "total": 0.000932293000005302, "count": 1, "is_parallel": true, "self": 0.0002530530000512954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006792399999540066, "count": 2, "is_parallel": true, "self": 0.0006792399999540066 } } } } } } }, "UnityEnvironment.step": { "total": 1901.7638914461668, "count": 231236, "is_parallel": true, "self": 60.57793804951666, "children": { "UnityEnvironment._generate_step_input": { "total": 84.43936231475402, "count": 231236, "is_parallel": true, "self": 84.43936231475402 }, "communicator.exchange": { "total": 1614.839244779936, "count": 231236, "is_parallel": true, "self": 1614.839244779936 }, "steps_from_proto": { "total": 141.90734630196016, "count": 231236, "is_parallel": true, "self": 46.992595106865906, "children": { "_process_rank_one_or_two_observation": { "total": 94.91475119509425, "count": 462472, "is_parallel": true, "self": 94.91475119509425 } } } } } } } } } } }, "trainer_advance": { "total": 1683.6247434840232, "count": 231237, "self": 13.470746638065066, "children": { "process_trajectory": { "total": 220.5565985369583, "count": 231237, "self": 219.00624482695775, "children": { "RLTrainer._checkpoint": { "total": 1.550353710000536, "count": 10, "self": 1.550353710000536 } } }, "_update_policy": { "total": 1449.5973983089998, "count": 97, "self": 420.16652889201237, "children": { "TorchPPOOptimizer.update": { "total": 1029.4308694169874, "count": 2910, "self": 1029.4308694169874 } } } } } } }, "trainer_threads": { "total": 1.1339998309267685e-06, "count": 1, "self": 1.1339998309267685e-06 }, "TrainerController._save_models": { "total": 0.15034288300012122, "count": 1, "self": 0.0032056379995992756, "children": { "RLTrainer._checkpoint": { "total": 0.14713724500052194, "count": 1, "self": 0.14713724500052194 } } } } } } }