{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073069095611572, "min": 1.4073069095611572, "max": 1.428281545639038, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70583.4765625, "min": 69390.671875, "max": 77131.5078125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 75.97692307692307, "min": 75.97692307692307, "max": 390.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49385.0, "min": 49296.0, "max": 50026.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999998.0, "min": 49830.0, "max": 1999998.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999998.0, "min": 49830.0, "max": 1999998.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.512145757675171, "min": 0.10395200550556183, "max": 2.512145757675171, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1632.894775390625, "min": 13.201904296875, "max": 1632.894775390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8963359208290393, "min": 1.7165676425761125, "max": 3.970260310966473, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2532.6183485388756, "min": 218.0040906071663, "max": 2532.6183485388756, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8963359208290393, "min": 1.7165676425761125, "max": 3.970260310966473, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2532.6183485388756, "min": 218.0040906071663, "max": 2532.6183485388756, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016821318129303917, "min": 0.013112786445223415, "max": 0.020587722197200894, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05046395438791175, "min": 0.02622557289044683, "max": 0.061763166591602685, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06068949219253328, "min": 0.022155783946315448, "max": 0.06423533815476629, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18206847657759984, "min": 0.044311567892630896, "max": 0.19270601446429886, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.592198802633332e-06, "min": 3.592198802633332e-06, "max": 0.00029526937657687496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0776596407899995e-05, "min": 1.0776596407899995e-05, "max": 0.0008436387187870999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119736666666668, "min": 0.10119736666666668, "max": 0.19842312499999992, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30359210000000003, "min": 0.20752684999999998, "max": 0.5812129000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.974859666666665e-05, "min": 6.974859666666665e-05, "max": 0.0049213139375000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020924578999999995, "min": 0.00020924578999999995, "max": 0.014062523709999998, "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": "1702720762", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702723239" }, "total": 2476.201828948, "count": 1, "self": 0.4417752150002343, "children": { "run_training.setup": { "total": 0.05061434700007794, "count": 1, "self": 0.05061434700007794 }, "TrainerController.start_learning": { "total": 2475.7094393859998, "count": 1, "self": 4.553790060042502, "children": { "TrainerController._reset_env": { "total": 3.2739571820000037, "count": 1, "self": 3.2739571820000037 }, "TrainerController.advance": { "total": 2467.705952751957, "count": 233001, "self": 4.927155483703245, "children": { "env_step": { "total": 1958.1033691390032, "count": 233001, "self": 1626.1554597489858, "children": { "SubprocessEnvManager._take_step": { "total": 329.0493029450437, "count": 233001, "self": 17.396710727084837, "children": { "TorchPolicy.evaluate": { "total": 311.65259221795884, "count": 222956, "self": 311.65259221795884 } } }, "workers": { "total": 2.898606444973666, "count": 233001, "self": 0.0, "children": { "worker_root": { "total": 2468.086202078029, "count": 233001, "is_parallel": true, "self": 1149.4960895511358, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006997110000384055, "count": 1, "is_parallel": true, "self": 0.0002273259999583388, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004723850000800667, "count": 2, "is_parallel": true, "self": 0.0004723850000800667 } } }, "UnityEnvironment.step": { "total": 0.055380621000040264, "count": 1, "is_parallel": true, "self": 0.00040060399999219953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020897400008834666, "count": 1, "is_parallel": true, "self": 0.00020897400008834666 }, "communicator.exchange": { "total": 0.05386280999994142, "count": 1, "is_parallel": true, "self": 0.05386280999994142 }, "steps_from_proto": { "total": 0.0009082330000182992, "count": 1, "is_parallel": true, "self": 0.00023491400008879282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006733189999295064, "count": 2, "is_parallel": true, "self": 0.0006733189999295064 } } } } } } }, "UnityEnvironment.step": { "total": 1318.5901125268933, "count": 233000, "is_parallel": true, "self": 41.33176255705757, "children": { "UnityEnvironment._generate_step_input": { "total": 84.82659755187751, "count": 233000, "is_parallel": true, "self": 84.82659755187751 }, "communicator.exchange": { "total": 1099.6355863939261, "count": 233000, "is_parallel": true, "self": 1099.6355863939261 }, "steps_from_proto": { "total": 92.79616602403212, "count": 233000, "is_parallel": true, "self": 34.30118595709166, "children": { "_process_rank_one_or_two_observation": { "total": 58.49498006694046, "count": 466000, "is_parallel": true, "self": 58.49498006694046 } } } } } } } } } } }, "trainer_advance": { "total": 504.6754281292501, "count": 233001, "self": 6.779768315292699, "children": { "process_trajectory": { "total": 160.5960491639554, "count": 233001, "self": 159.31503823695527, "children": { "RLTrainer._checkpoint": { "total": 1.2810109270001249, "count": 10, "self": 1.2810109270001249 } } }, "_update_policy": { "total": 337.299610650002, "count": 97, "self": 272.31071101399004, "children": { "TorchPPOOptimizer.update": { "total": 64.98889963601198, "count": 2910, "self": 64.98889963601198 } } } } } } }, "trainer_threads": { "total": 1.5670002539991401e-06, "count": 1, "self": 1.5670002539991401e-06 }, "TrainerController._save_models": { "total": 0.17573782499994195, "count": 1, "self": 0.002182052000080148, "children": { "RLTrainer._checkpoint": { "total": 0.1735557729998618, "count": 1, "self": 0.1735557729998618 } } } } } } }