{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4080497026443481, "min": 1.4080497026443481, "max": 1.430041790008545, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70984.0078125, "min": 69119.8671875, "max": 76274.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.3996983408748, "min": 70.36901408450704, "max": 421.3529411764706, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49327.0, "min": 48679.0, "max": 50196.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999952.0, "min": 49979.0, "max": 1999952.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999952.0, "min": 49979.0, "max": 1999952.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4622294902801514, "min": 0.08340884000062943, "max": 2.490427017211914, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1632.4581298828125, "min": 9.842243194580078, "max": 1730.76171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8365571077233165, "min": 1.8127749632980863, "max": 4.013846931339561, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2543.637362420559, "min": 213.9074456691742, "max": 2677.2359032034874, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8365571077233165, "min": 1.8127749632980863, "max": 4.013846931339561, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2543.637362420559, "min": 213.9074456691742, "max": 2677.2359032034874, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015480251178269101, "min": 0.0135873673572443, "max": 0.020147646496863875, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.046440753534807304, "min": 0.0271747347144886, "max": 0.060442939490591624, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05628210600051615, "min": 0.023386964201927186, "max": 0.0621735035131375, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16884631800154845, "min": 0.04677392840385437, "max": 0.17787815009554225, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.836348721249996e-06, "min": 3.836348721249996e-06, "max": 0.00029531122656292503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1509046163749987e-05, "min": 1.1509046163749987e-05, "max": 0.0008439913686695498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127875000000003, "min": 0.10127875000000003, "max": 0.19843707499999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038362500000001, "min": 0.20769505, "max": 0.5813304500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.380962499999995e-05, "min": 7.380962499999995e-05, "max": 0.004922010042499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022142887499999986, "min": 0.00022142887499999986, "max": 0.014068389454999997, "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": "1688047650", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688050136" }, "total": 2485.708863916, "count": 1, "self": 0.38850319000039235, "children": { "run_training.setup": { "total": 0.04240222399994309, "count": 1, "self": 0.04240222399994309 }, "TrainerController.start_learning": { "total": 2485.277958502, "count": 1, "self": 4.5803424399937285, "children": { "TrainerController._reset_env": { "total": 4.010024188999978, "count": 1, "self": 4.010024188999978 }, "TrainerController.advance": { "total": 2476.5714765430066, "count": 233232, "self": 4.677444626039687, "children": { "env_step": { "total": 1943.5293740359932, "count": 233232, "self": 1640.7761646237905, "children": { "SubprocessEnvManager._take_step": { "total": 299.848153640076, "count": 233232, "self": 17.399913984035834, "children": { "TorchPolicy.evaluate": { "total": 282.4482396560402, "count": 222966, "self": 282.4482396560402 } } }, "workers": { "total": 2.9050557721268433, "count": 233232, "self": 0.0, "children": { "worker_root": { "total": 2477.278554320056, "count": 233232, "is_parallel": true, "self": 1134.9912932360476, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009173360000431785, "count": 1, "is_parallel": true, "self": 0.0002457939999658265, "children": { "_process_rank_one_or_two_observation": { "total": 0.000671542000077352, "count": 2, "is_parallel": true, "self": 0.000671542000077352 } } }, "UnityEnvironment.step": { "total": 0.031110005999948953, "count": 1, "is_parallel": true, "self": 0.0003392139998368293, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016703400001460977, "count": 1, "is_parallel": true, "self": 0.00016703400001460977 }, "communicator.exchange": { "total": 0.02980491300002086, "count": 1, "is_parallel": true, "self": 0.02980491300002086 }, "steps_from_proto": { "total": 0.0007988450000766534, "count": 1, "is_parallel": true, "self": 0.00025805900008890603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005407859999877473, "count": 2, "is_parallel": true, "self": 0.0005407859999877473 } } } } } } }, "UnityEnvironment.step": { "total": 1342.2872610840086, "count": 233231, "is_parallel": true, "self": 39.908772314937096, "children": { "UnityEnvironment._generate_step_input": { "total": 83.037694250002, "count": 233231, "is_parallel": true, "self": 83.037694250002 }, "communicator.exchange": { "total": 1121.2057378340746, "count": 233231, "is_parallel": true, "self": 1121.2057378340746 }, "steps_from_proto": { "total": 98.13505668499488, "count": 233231, "is_parallel": true, "self": 37.16797821102671, "children": { "_process_rank_one_or_two_observation": { "total": 60.96707847396817, "count": 466462, "is_parallel": true, "self": 60.96707847396817 } } } } } } } } } } }, "trainer_advance": { "total": 528.3646578809735, "count": 233232, "self": 6.6951001519552165, "children": { "process_trajectory": { "total": 145.68000810801823, "count": 233232, "self": 144.3538276980181, "children": { "RLTrainer._checkpoint": { "total": 1.32618041000012, "count": 10, "self": 1.32618041000012 } } }, "_update_policy": { "total": 375.98954962100004, "count": 97, "self": 316.6864813639943, "children": { "TorchPPOOptimizer.update": { "total": 59.30306825700575, "count": 2910, "self": 59.30306825700575 } } } } } } }, "trainer_threads": { "total": 1.0219996511295903e-06, "count": 1, "self": 1.0219996511295903e-06 }, "TrainerController._save_models": { "total": 0.11611430799985101, "count": 1, "self": 0.0021593169999505335, "children": { "RLTrainer._checkpoint": { "total": 0.11395499099990047, "count": 1, "self": 0.11395499099990047 } } } } } } }