{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4049372673034668, "min": 1.4049372673034668, "max": 1.4286155700683594, "count": 39 }, "Huggy.Policy.Entropy.sum": { "value": 70173.8046875, "min": 67885.1875, "max": 76982.0546875, "count": 39 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.31, "min": 75.29555895865238, "max": 420.0083333333333, "count": 39 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49386.0, "min": 49085.0, "max": 50401.0, "count": 39 }, "Huggy.Step.mean": { "value": 1949906.0, "min": 49999.0, "max": 1949906.0, "count": 39 }, "Huggy.Step.sum": { "value": 1949906.0, "min": 49999.0, "max": 1949906.0, "count": 39 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.446791887283325, "min": 0.09747413545846939, "max": 2.4741194248199463, "count": 39 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1468.0750732421875, "min": 11.599422454833984, "max": 1601.995849609375, "count": 39 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7988817846775054, "min": 1.837012348806157, "max": 3.976086442073186, "count": 39 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2279.3290708065033, "min": 218.60446950793266, "max": 2522.521385014057, "count": 39 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7988817846775054, "min": 1.837012348806157, "max": 3.976086442073186, "count": 39 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2279.3290708065033, "min": 218.60446950793266, "max": 2522.521385014057, "count": 39 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018656118672030667, "min": 0.012707770229462767, "max": 0.020685278445792696, "count": 39 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03731223734406133, "min": 0.025415540458925533, "max": 0.05219667065975954, "count": 39 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05366541085143884, "min": 0.021912601217627524, "max": 0.059947727185984456, "count": 39 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10733082170287768, "min": 0.04382520243525505, "max": 0.1781808293114106, "count": 39 }, "Huggy.Policy.LearningRate.mean": { "value": 1.1567946144050005e-05, "min": 1.1567946144050005e-05, "max": 0.00029527395157534996, "count": 39 }, "Huggy.Policy.LearningRate.sum": { "value": 2.313589228810001e-05, "min": 2.313589228810001e-05, "max": 0.0008436718687760501, "count": 39 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10385595, "min": 0.10385595, "max": 0.19842465000000004, "count": 39 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2077119, "min": 0.2077119, "max": 0.5812239499999998, "count": 39 }, "Huggy.Policy.Beta.mean": { "value": 0.00020241190500000018, "min": 0.00020241190500000018, "max": 0.004921390035000001, "count": 39 }, "Huggy.Policy.Beta.sum": { "value": 0.00040482381000000035, "min": 0.00040482381000000035, "max": 0.014063075104999996, "count": 39 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 39 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 39 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670764317", "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": "1670766462" }, "total": 2145.0520965799997, "count": 1, "self": 10.008713797999462, "children": { "run_training.setup": { "total": 0.105532390999997, "count": 1, "self": 0.105532390999997 }, "TrainerController.start_learning": { "total": 2134.937850391, "count": 1, "self": 3.7903234859554686, "children": { "TrainerController._reset_env": { "total": 10.83409558400001, "count": 1, "self": 10.83409558400001 }, "TrainerController.advance": { "total": 2120.130292083045, "count": 227242, "self": 4.046155947153238, "children": { "env_step": { "total": 1668.3730619499931, "count": 227242, "self": 1400.8124546220502, "children": { "SubprocessEnvManager._take_step": { "total": 265.05734577899784, "count": 227242, "self": 13.910732319060457, "children": { "TorchPolicy.evaluate": { "total": 251.14661345993738, "count": 217558, "self": 63.41278021890196, "children": { "TorchPolicy.sample_actions": { "total": 187.73383324103543, "count": 217558, "self": 187.73383324103543 } } } } }, "workers": { "total": 2.5032615489450336, "count": 227241, "self": 0.0, "children": { "worker_root": { "total": 2127.3495334590534, "count": 227241, "is_parallel": true, "self": 977.2002030890801, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022285759999931543, "count": 1, "is_parallel": true, "self": 0.00029063800002404605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019379379999691082, "count": 2, "is_parallel": true, "self": 0.0019379379999691082 } } }, "UnityEnvironment.step": { "total": 0.02690880299996934, "count": 1, "is_parallel": true, "self": 0.00029030199993940187, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017719400000260066, "count": 1, "is_parallel": true, "self": 0.00017719400000260066 }, "communicator.exchange": { "total": 0.025706061000050795, "count": 1, "is_parallel": true, "self": 0.025706061000050795 }, "steps_from_proto": { "total": 0.0007352459999765415, "count": 1, "is_parallel": true, "self": 0.0002660990001004393, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004691469998761022, "count": 2, "is_parallel": true, "self": 0.0004691469998761022 } } } } } } }, "UnityEnvironment.step": { "total": 1150.1493303699733, "count": 227240, "is_parallel": true, "self": 33.5120115350594, "children": { "UnityEnvironment._generate_step_input": { "total": 74.0062600799472, "count": 227240, "is_parallel": true, "self": 74.0062600799472 }, "communicator.exchange": { "total": 952.8639262280135, "count": 227240, "is_parallel": true, "self": 952.8639262280135 }, "steps_from_proto": { "total": 89.76713252695322, "count": 227240, "is_parallel": true, "self": 36.901885798056014, "children": { "_process_rank_one_or_two_observation": { "total": 52.865246728897205, "count": 454480, "is_parallel": true, "self": 52.865246728897205 } } } } } } } } } } }, "trainer_advance": { "total": 447.71107418589827, "count": 227241, "self": 5.857419967037117, "children": { "process_trajectory": { "total": 142.15309032286166, "count": 227241, "self": 141.80509532086137, "children": { "RLTrainer._checkpoint": { "total": 0.3479950020002889, "count": 3, "self": 0.3479950020002889 } } }, "_update_policy": { "total": 299.7005638959995, "count": 94, "self": 248.01190740500692, "children": { "TorchPPOOptimizer.update": { "total": 51.68865649099257, "count": 2820, "self": 51.68865649099257 } } } } } } }, "trainer_threads": { "total": 1.475999852118548e-06, "count": 1, "self": 1.475999852118548e-06 }, "TrainerController._save_models": { "total": 0.1831377620001149, "count": 1, "self": 0.0028474350001488347, "children": { "RLTrainer._checkpoint": { "total": 0.18029032699996606, "count": 1, "self": 0.18029032699996606 } } } } } } }