{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.411651372909546, "min": 1.411651372909546, "max": 1.4296573400497437, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71621.546875, "min": 69218.234375, "max": 75838.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.87874015748031, "min": 76.06163328197226, "max": 417.4876033057851, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49453.0, "min": 49263.0, "max": 50516.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49971.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49971.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4654488563537598, "min": 0.1950099915266037, "max": 2.521068572998047, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1565.56005859375, "min": 23.401199340820312, "max": 1604.7603759765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.884080209131316, "min": 1.9252391355733076, "max": 4.039583942691485, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2466.3909327983856, "min": 231.02869626879692, "max": 2517.8030250668526, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.884080209131316, "min": 1.9252391355733076, "max": 4.039583942691485, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2466.3909327983856, "min": 231.02869626879692, "max": 2517.8030250668526, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01634865562664345, "min": 0.01346710238412925, "max": 0.0195508500417418, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04904596687993035, "min": 0.028952211355014395, "max": 0.055422236845940165, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06307654678821563, "min": 0.018291273154318333, "max": 0.06307654678821563, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1892296403646469, "min": 0.036582546308636665, "max": 0.1892296403646469, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.437898854066669e-06, "min": 3.437898854066669e-06, "max": 0.00029530815156394996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0313696562200007e-05, "min": 1.0313696562200007e-05, "max": 0.0008438056687314499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114593333333333, "min": 0.10114593333333333, "max": 0.19843605000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034378, "min": 0.20745479999999997, "max": 0.5812685499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.718207333333338e-05, "min": 6.718207333333338e-05, "max": 0.004921958894999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020154622000000014, "min": 0.00020154622000000014, "max": 0.014065300644999997, "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": "1707938580", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707941081" }, "total": 2501.608854115, "count": 1, "self": 0.7273605760001374, "children": { "run_training.setup": { "total": 0.052426893000074415, "count": 1, "self": 0.052426893000074415 }, "TrainerController.start_learning": { "total": 2500.829066646, "count": 1, "self": 4.734674091958368, "children": { "TrainerController._reset_env": { "total": 3.0500406399999065, "count": 1, "self": 3.0500406399999065 }, "TrainerController.advance": { "total": 2492.8705033900414, "count": 232550, "self": 5.264897502004715, "children": { "env_step": { "total": 2002.333257510904, "count": 232550, "self": 1657.1624796621525, "children": { "SubprocessEnvManager._take_step": { "total": 342.03958438985546, "count": 232550, "self": 18.140610484959552, "children": { "TorchPolicy.evaluate": { "total": 323.8989739048959, "count": 222902, "self": 323.8989739048959 } } }, "workers": { "total": 3.1311934588961776, "count": 232550, "self": 0.0, "children": { "worker_root": { "total": 2493.252231387039, "count": 232550, "is_parallel": true, "self": 1149.292371917024, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009239409998826886, "count": 1, "is_parallel": true, "self": 0.0002597359998617321, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006642050000209565, "count": 2, "is_parallel": true, "self": 0.0006642050000209565 } } }, "UnityEnvironment.step": { "total": 0.05475487700005033, "count": 1, "is_parallel": true, "self": 0.00031312199985222833, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019642200004454935, "count": 1, "is_parallel": true, "self": 0.00019642200004454935 }, "communicator.exchange": { "total": 0.05352923800001008, "count": 1, "is_parallel": true, "self": 0.05352923800001008 }, "steps_from_proto": { "total": 0.0007160950001434685, "count": 1, "is_parallel": true, "self": 0.00019760200007112871, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005184930000723398, "count": 2, "is_parallel": true, "self": 0.0005184930000723398 } } } } } } }, "UnityEnvironment.step": { "total": 1343.959859470015, "count": 232549, "is_parallel": true, "self": 42.076184961269746, "children": { "UnityEnvironment._generate_step_input": { "total": 88.3306017839925, "count": 232549, "is_parallel": true, "self": 88.3306017839925 }, "communicator.exchange": { "total": 1117.9471455329638, "count": 232549, "is_parallel": true, "self": 1117.9471455329638 }, "steps_from_proto": { "total": 95.60592719178908, "count": 232549, "is_parallel": true, "self": 35.98978155385953, "children": { "_process_rank_one_or_two_observation": { "total": 59.61614563792955, "count": 465098, "is_parallel": true, "self": 59.61614563792955 } } } } } } } } } } }, "trainer_advance": { "total": 485.27234837713263, "count": 232550, "self": 7.065113675137127, "children": { "process_trajectory": { "total": 162.96692162899103, "count": 232550, "self": 161.71655606399077, "children": { "RLTrainer._checkpoint": { "total": 1.2503655650002656, "count": 10, "self": 1.2503655650002656 } } }, "_update_policy": { "total": 315.2403130730045, "count": 97, "self": 252.65214949599226, "children": { "TorchPPOOptimizer.update": { "total": 62.58816357701221, "count": 2910, "self": 62.58816357701221 } } } } } } }, "trainer_threads": { "total": 1.531000634713564e-06, "count": 1, "self": 1.531000634713564e-06 }, "TrainerController._save_models": { "total": 0.17384699299964268, "count": 1, "self": 0.0030834669996693265, "children": { "RLTrainer._checkpoint": { "total": 0.17076352599997335, "count": 1, "self": 0.17076352599997335 } } } } } } }