{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4098167419433594, "min": 1.4098167419433594, "max": 1.4305479526519775, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70511.984375, "min": 68518.4453125, "max": 78818.140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.96521739130435, "min": 73.16, "max": 412.5123966942149, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49430.0, "min": 48801.0, "max": 50108.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999936.0, "min": 49941.0, "max": 1999936.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999936.0, "min": 49941.0, "max": 1999936.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4437954425811768, "min": 0.12018474191427231, "max": 2.537317991256714, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1405.182373046875, "min": 14.422168731689453, "max": 1669.974365234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.740905201124108, "min": 1.8461370470623175, "max": 4.091703290361107, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2151.0204906463623, "min": 221.5364456474781, "max": 2607.098845601082, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.740905201124108, "min": 1.8461370470623175, "max": 4.091703290361107, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2151.0204906463623, "min": 221.5364456474781, "max": 2607.098845601082, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015244625796670639, "min": 0.013519172063711773, "max": 0.020171436222153713, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04573387739001192, "min": 0.027055011503398417, "max": 0.06016653329352266, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054649477659000294, "min": 0.021984741309036812, "max": 0.0625292602305611, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16394843297700087, "min": 0.043969482618073624, "max": 0.18435671168069045, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6132987955999934e-06, "min": 3.6132987955999934e-06, "max": 0.00029538000153999993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.083989638679998e-05, "min": 1.083989638679998e-05, "max": 0.0008439780186740001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120440000000001, "min": 0.10120440000000001, "max": 0.19846, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036132, "min": 0.20758565000000007, "max": 0.581326, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.009955999999992e-05, "min": 7.009955999999992e-05, "max": 0.004923154, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021029867999999976, "min": 0.00021029867999999976, "max": 0.014068167400000001, "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": "1677447795", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677450265" }, "total": 2470.4366212, "count": 1, "self": 0.4578234590003376, "children": { "run_training.setup": { "total": 0.18002023400003964, "count": 1, "self": 0.18002023400003964 }, "TrainerController.start_learning": { "total": 2469.7987775069996, "count": 1, "self": 4.426384313097515, "children": { "TrainerController._reset_env": { "total": 11.590374876999931, "count": 1, "self": 11.590374876999931 }, "TrainerController.advance": { "total": 2453.6748268699025, "count": 233472, "self": 4.73923890384367, "children": { "env_step": { "total": 1917.0830407510173, "count": 233472, "self": 1606.6004030490494, "children": { "SubprocessEnvManager._take_step": { "total": 307.5491682848501, "count": 233472, "self": 16.768967041891756, "children": { "TorchPolicy.evaluate": { "total": 290.78020124295836, "count": 223060, "self": 72.50371296503886, "children": { "TorchPolicy.sample_actions": { "total": 218.2764882779195, "count": 223060, "self": 218.2764882779195 } } } } }, "workers": { "total": 2.933469417117749, "count": 233472, "self": 0.0, "children": { "worker_root": { "total": 2460.9178360741053, "count": 233472, "is_parallel": true, "self": 1160.0907892130795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012027469999793539, "count": 1, "is_parallel": true, "self": 0.00046407000013459765, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007386769998447562, "count": 2, "is_parallel": true, "self": 0.0007386769998447562 } } }, "UnityEnvironment.step": { "total": 0.04267179900011797, "count": 1, "is_parallel": true, "self": 0.0002915509999183996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004084580000380811, "count": 1, "is_parallel": true, "self": 0.0004084580000380811 }, "communicator.exchange": { "total": 0.0401163640001414, "count": 1, "is_parallel": true, "self": 0.0401163640001414 }, "steps_from_proto": { "total": 0.0018554260000200884, "count": 1, "is_parallel": true, "self": 0.0002580799998668226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015973460001532658, "count": 2, "is_parallel": true, "self": 0.0015973460001532658 } } } } } } }, "UnityEnvironment.step": { "total": 1300.8270468610258, "count": 233471, "is_parallel": true, "self": 39.161710540960485, "children": { "UnityEnvironment._generate_step_input": { "total": 85.08106487010764, "count": 233471, "is_parallel": true, "self": 85.08106487010764 }, "communicator.exchange": { "total": 1082.2871212559921, "count": 233471, "is_parallel": true, "self": 1082.2871212559921 }, "steps_from_proto": { "total": 94.29715019396554, "count": 233471, "is_parallel": true, "self": 40.58614418691195, "children": { "_process_rank_one_or_two_observation": { "total": 53.711006007053584, "count": 466942, "is_parallel": true, "self": 53.711006007053584 } } } } } } } } } } }, "trainer_advance": { "total": 531.8525472150418, "count": 233472, "self": 6.667947783959562, "children": { "process_trajectory": { "total": 175.83942171508534, "count": 233472, "self": 174.67745234908534, "children": { "RLTrainer._checkpoint": { "total": 1.161969365999994, "count": 10, "self": 1.161969365999994 } } }, "_update_policy": { "total": 349.3451777159969, "count": 97, "self": 292.5001469020133, "children": { "TorchPPOOptimizer.update": { "total": 56.84503081398361, "count": 2910, "self": 56.84503081398361 } } } } } } }, "trainer_threads": { "total": 7.950002327561378e-07, "count": 1, "self": 7.950002327561378e-07 }, "TrainerController._save_models": { "total": 0.10719065199918987, "count": 1, "self": 0.002031002999501652, "children": { "RLTrainer._checkpoint": { "total": 0.10515964899968822, "count": 1, "self": 0.10515964899968822 } } } } } } }