{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404373288154602, "min": 1.404361367225647, "max": 1.4263784885406494, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70328.203125, "min": 68223.234375, "max": 78748.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.89857142857143, "min": 69.83711048158641, "max": 385.92248062015506, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48929.0, "min": 48877.0, "max": 50052.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999947.0, "min": 49442.0, "max": 1999947.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999947.0, "min": 49442.0, "max": 1999947.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.512916088104248, "min": 0.1481183022260666, "max": 2.5530056953430176, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1759.041259765625, "min": 19.107261657714844, "max": 1771.1202392578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9520345956938607, "min": 1.5815874114055042, "max": 4.113517676173029, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2766.4242169857025, "min": 204.02477607131004, "max": 2807.2465031147003, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9520345956938607, "min": 1.5815874114055042, "max": 4.113517676173029, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2766.4242169857025, "min": 204.02477607131004, "max": 2807.2465031147003, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014680468631882429, "min": 0.01221238792738101, "max": 0.019772650332500537, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.044041405895647284, "min": 0.02442477585476202, "max": 0.05711166349016518, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0667079195794132, "min": 0.020025422982871532, "max": 0.0667079195794132, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.2001237587382396, "min": 0.040050845965743063, "max": 0.2001237587382396, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.905898698066671e-06, "min": 3.905898698066671e-06, "max": 0.00029534767655077493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1717696094200013e-05, "min": 1.1717696094200013e-05, "max": 0.0008441694186102001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130193333333333, "min": 0.10130193333333333, "max": 0.198449225, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039058, "min": 0.20773525000000004, "max": 0.5813897999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.496647333333341e-05, "min": 7.496647333333341e-05, "max": 0.0049226163275000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022489942000000025, "min": 0.00022489942000000025, "max": 0.014071351020000001, "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": "1712919282", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712921627" }, "total": 2345.3814327669998, "count": 1, "self": 0.4414670989995102, "children": { "run_training.setup": { "total": 0.05598695700018652, "count": 1, "self": 0.05598695700018652 }, "TrainerController.start_learning": { "total": 2344.883978711, "count": 1, "self": 4.192715773080636, "children": { "TrainerController._reset_env": { "total": 3.524502126000016, "count": 1, "self": 3.524502126000016 }, "TrainerController.advance": { "total": 2337.0564699399197, "count": 233756, "self": 4.424220454114675, "children": { "env_step": { "total": 1847.9526558848413, "count": 233756, "self": 1537.0609487699696, "children": { "SubprocessEnvManager._take_step": { "total": 308.21379705088793, "count": 233756, "self": 15.35844489282158, "children": { "TorchPolicy.evaluate": { "total": 292.85535215806635, "count": 222947, "self": 292.85535215806635 } } }, "workers": { "total": 2.677910063983745, "count": 233756, "self": 0.0, "children": { "worker_root": { "total": 2337.835601268104, "count": 233756, "is_parallel": true, "self": 1094.172255331019, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008751660000143602, "count": 1, "is_parallel": true, "self": 0.00021220000007815543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006629659999362048, "count": 2, "is_parallel": true, "self": 0.0006629659999362048 } } }, "UnityEnvironment.step": { "total": 0.028884875999892756, "count": 1, "is_parallel": true, "self": 0.0003826590000244323, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021988499997860345, "count": 1, "is_parallel": true, "self": 0.00021988499997860345 }, "communicator.exchange": { "total": 0.027540971999997055, "count": 1, "is_parallel": true, "self": 0.027540971999997055 }, "steps_from_proto": { "total": 0.0007413599998926657, "count": 1, "is_parallel": true, "self": 0.00019171899975845008, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005496410001342156, "count": 2, "is_parallel": true, "self": 0.0005496410001342156 } } } } } } }, "UnityEnvironment.step": { "total": 1243.6633459370848, "count": 233755, "is_parallel": true, "self": 38.88269274807453, "children": { "UnityEnvironment._generate_step_input": { "total": 79.98668020790501, "count": 233755, "is_parallel": true, "self": 79.98668020790501 }, "communicator.exchange": { "total": 1035.2112825440613, "count": 233755, "is_parallel": true, "self": 1035.2112825440613 }, "steps_from_proto": { "total": 89.582690437044, "count": 233755, "is_parallel": true, "self": 31.889287401177853, "children": { "_process_rank_one_or_two_observation": { "total": 57.69340303586614, "count": 467510, "is_parallel": true, "self": 57.69340303586614 } } } } } } } } } } }, "trainer_advance": { "total": 484.6795936009637, "count": 233756, "self": 6.331254487928618, "children": { "process_trajectory": { "total": 152.82901476303687, "count": 233756, "self": 151.57054647703671, "children": { "RLTrainer._checkpoint": { "total": 1.2584682860001521, "count": 10, "self": 1.2584682860001521 } } }, "_update_policy": { "total": 325.5193243499982, "count": 97, "self": 262.1877360689987, "children": { "TorchPPOOptimizer.update": { "total": 63.33158828099954, "count": 2910, "self": 63.33158828099954 } } } } } } }, "trainer_threads": { "total": 1.1389997780497652e-06, "count": 1, "self": 1.1389997780497652e-06 }, "TrainerController._save_models": { "total": 0.11028973299971767, "count": 1, "self": 0.0021379629993134586, "children": { "RLTrainer._checkpoint": { "total": 0.10815177000040421, "count": 1, "self": 0.10815177000040421 } } } } } } }