{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5988489985466003, "min": 0.5933086276054382, "max": 1.4872267246246338, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17946.306640625, "min": 17894.1875, "max": 45116.51171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.481211394071579, "min": -0.10440889000892639, "max": 0.481211394071579, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.88949584960938, "min": -25.16254234313965, "max": 130.88949584960938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6783701777458191, "min": -0.0076231397688388824, "max": 0.6783701777458191, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 184.51669311523438, "min": -2.0125088691711426, "max": 184.51669311523438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06827529051160025, "min": 0.06307274020111145, "max": 0.07357827044740718, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0241293576740038, "min": 0.5067426238758301, "max": 1.0680784137512092, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04244145836066333, "min": 0.0006460087532170913, "max": 0.04244145836066333, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.6366218754099499, "min": 0.006460087532170913, "max": 0.6366218754099499, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.457997514033333e-06, "min": 7.457997514033333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011186996271049999, "min": 0.00011186996271049999, "max": 0.0035080808306398, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248596666666665, "min": 0.10248596666666665, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372894999999998, "min": 1.3886848, "max": 2.5693602, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025834807, "min": 0.00025834807, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038752210499999997, "min": 0.0038752210499999997, "max": 0.11695908398000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010281241498887539, "min": 0.010246685706079006, "max": 0.4301857650279999, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1542186290025711, "min": 0.14345359802246094, "max": 3.0113003253936768, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.5810810810811, "min": 407.2916666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30605.0, "min": 15984.0, "max": 32472.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5301698363602978, "min": -1.0000000521540642, "max": 1.5371249825176265, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.70239805430174, "min": -31.998801663517952, "max": 111.70239805430174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5301698363602978, "min": -1.0000000521540642, "max": 1.5371249825176265, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.70239805430174, "min": -31.998801663517952, "max": 111.70239805430174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044983924890602045, "min": 0.042888374927214395, "max": 8.836109410971403, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2838265170139493, "min": 3.0879629947594367, "max": 141.37775057554245, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705892974", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/roboto/Software/.miniconda/envs/HFRL/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=/home/roboto/Software/ml-agents-custom-envs/Pyramids/Pyramids --run-id=PyramidsRND1 --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2", "numpy_version": "1.21.2", "end_time_seconds": "1705893991" }, "total": 1017.1194010039981, "count": 1, "self": 0.2225831519899657, "children": { "run_training.setup": { "total": 0.028597574004379567, "count": 1, "self": 0.028597574004379567 }, "TrainerController.start_learning": { "total": 1016.8682202780037, "count": 1, "self": 0.9000508326280396, "children": { "TrainerController._reset_env": { "total": 1.6972173710018978, "count": 1, "self": 1.6972173710018978 }, "TrainerController.advance": { "total": 1014.2042314823702, "count": 63587, "self": 0.864853381892317, "children": { "env_step": { "total": 617.8282273138975, "count": 63587, "self": 537.0176488008656, "children": { "SubprocessEnvManager._take_step": { "total": 80.23423510571592, "count": 63587, "self": 2.6079646441794466, "children": { "TorchPolicy.evaluate": { "total": 77.62627046153648, "count": 62551, "self": 77.62627046153648 } } }, "workers": { "total": 0.576343407316017, "count": 63587, "self": 0.0, "children": { "worker_root": { "total": 1015.655027100991, "count": 63587, "is_parallel": true, "self": 539.5224102654174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001152196004113648, "count": 1, "is_parallel": true, "self": 0.0003147429961245507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008374530079890974, "count": 8, "is_parallel": true, "self": 0.0008374530079890974 } } }, "UnityEnvironment.step": { "total": 0.020997147999878507, "count": 1, "is_parallel": true, "self": 0.00021216900495346636, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018454500241205096, "count": 1, "is_parallel": true, "self": 0.00018454500241205096 }, "communicator.exchange": { "total": 0.019895653997082263, "count": 1, "is_parallel": true, "self": 0.019895653997082263 }, "steps_from_proto": { "total": 0.0007047799954307266, "count": 1, "is_parallel": true, "self": 0.00016030400001909584, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005444759954116307, "count": 8, "is_parallel": true, "self": 0.0005444759954116307 } } } } } } }, "UnityEnvironment.step": { "total": 476.1326168355736, "count": 63586, "is_parallel": true, "self": 13.56466836976324, "children": { "UnityEnvironment._generate_step_input": { "total": 9.321511581125378, "count": 63586, "is_parallel": true, "self": 9.321511581125378 }, "communicator.exchange": { "total": 411.7634569061265, "count": 63586, "is_parallel": true, "self": 411.7634569061265 }, "steps_from_proto": { "total": 41.48297997855843, "count": 63586, "is_parallel": true, "self": 9.323108403979859, "children": { "_process_rank_one_or_two_observation": { "total": 32.159871574578574, "count": 508688, "is_parallel": true, "self": 32.159871574578574 } } } } } } } } } } }, "trainer_advance": { "total": 395.5111507865804, "count": 63587, "self": 1.6635004440249759, "children": { "process_trajectory": { "total": 65.84950050560292, "count": 63587, "self": 65.7405681556047, "children": { "RLTrainer._checkpoint": { "total": 0.10893234999821289, "count": 2, "self": 0.10893234999821289 } } }, "_update_policy": { "total": 327.9981498369525, "count": 450, "self": 201.79749540099147, "children": { "TorchPPOOptimizer.update": { "total": 126.20065443596104, "count": 22728, "self": 126.20065443596104 } } } } } } }, "trainer_threads": { "total": 6.580012268386781e-07, "count": 1, "self": 6.580012268386781e-07 }, "TrainerController._save_models": { "total": 0.06671993400232168, "count": 1, "self": 0.0013269190021674149, "children": { "RLTrainer._checkpoint": { "total": 0.06539301500015426, "count": 1, "self": 0.06539301500015426 } } } } } } }