{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35506144165992737, "min": 0.35506144165992737, "max": 1.463525414466858, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10720.0146484375, "min": 10720.0146484375, "max": 44397.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29907.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29907.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6622282862663269, "min": -0.17273637652397156, "max": 0.6912947297096252, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.3972930908203, "min": -40.93852233886719, "max": 197.71029663085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04751909524202347, "min": -0.042051222175359726, "max": 0.5015222430229187, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.590461730957031, "min": -11.059471130371094, "max": 118.86077117919922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06738142093499414, "min": 0.0629620737620696, "max": 0.07448972930239164, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9433398930899178, "min": 0.5075800836773057, "max": 1.078963831555573, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015459975011513699, "min": 0.0003894497554395022, "max": 0.016911163263665957, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2164396501611918, "min": 0.004283947309834524, "max": 0.2367562856913234, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.290418998464285e-06, "min": 7.290418998464285e-06, "max": 0.0002952342015886, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010206586597849999, "min": 0.00010206586597849999, "max": 0.0036336283887906, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243010714285715, "min": 0.10243010714285715, "max": 0.1984114, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340215, "min": 1.3888798, "max": 2.6112094000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002527677035714286, "min": 0.0002527677035714286, "max": 0.00984129886, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00353874785, "min": 0.00353874785, "max": 0.12113981906000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010068492963910103, "min": 0.009819133207201958, "max": 0.45580556988716125, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14095890522003174, "min": 0.14095890522003174, "max": 3.190639019012451, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 295.2621359223301, "min": 293.84761904761905, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30412.0, "min": 16833.0, "max": 32658.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7047378442530494, "min": -0.9999667187531789, "max": 1.7047378442530494, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 175.58799795806408, "min": -29.999001562595367, "max": 177.14539821445942, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7047378442530494, "min": -0.9999667187531789, "max": 1.7047378442530494, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 175.58799795806408, "min": -29.999001562595367, "max": 177.14539821445942, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030839846128410234, "min": 0.030839846128410234, "max": 8.585498290757338, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.176504151226254, "min": 3.039861105324235, "max": 154.5389692336321, "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": "1696106501", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1696108804" }, "total": 2302.896412596, "count": 1, "self": 0.4837327370000821, "children": { "run_training.setup": { "total": 0.041406192000067676, "count": 1, "self": 0.041406192000067676 }, "TrainerController.start_learning": { "total": 2302.371273667, "count": 1, "self": 1.3518194669727563, "children": { "TrainerController._reset_env": { "total": 4.134000729000036, "count": 1, "self": 4.134000729000036 }, "TrainerController.advance": { "total": 2296.7918288880273, "count": 64132, "self": 1.3402883102226042, "children": { "env_step": { "total": 1620.3482099539094, "count": 64132, "self": 1513.3123293190133, "children": { "SubprocessEnvManager._take_step": { "total": 106.23248428497709, "count": 64132, "self": 4.747561928024652, "children": { "TorchPolicy.evaluate": { "total": 101.48492235695244, "count": 62558, "self": 101.48492235695244 } } }, "workers": { "total": 0.8033963499190122, "count": 64132, "self": 0.0, "children": { "worker_root": { "total": 2297.1867932109885, "count": 64132, "is_parallel": true, "self": 898.2543924839615, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017446230001496588, "count": 1, "is_parallel": true, "self": 0.0005505770000127086, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011940460001369502, "count": 8, "is_parallel": true, "self": 0.0011940460001369502 } } }, "UnityEnvironment.step": { "total": 0.06166582299988477, "count": 1, "is_parallel": true, "self": 0.0005924280001181614, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005105230000026495, "count": 1, "is_parallel": true, "self": 0.0005105230000026495 }, "communicator.exchange": { "total": 0.05459802299992589, "count": 1, "is_parallel": true, "self": 0.05459802299992589 }, "steps_from_proto": { "total": 0.005964848999838068, "count": 1, "is_parallel": true, "self": 0.00042595300010361825, "children": { "_process_rank_one_or_two_observation": { "total": 0.00553889599973445, "count": 8, "is_parallel": true, "self": 0.00553889599973445 } } } } } } }, "UnityEnvironment.step": { "total": 1398.932400727027, "count": 64131, "is_parallel": true, "self": 33.99760372505193, "children": { "UnityEnvironment._generate_step_input": { "total": 22.82374419592884, "count": 64131, "is_parallel": true, "self": 22.82374419592884 }, "communicator.exchange": { "total": 1236.399067592062, "count": 64131, "is_parallel": true, "self": 1236.399067592062 }, "steps_from_proto": { "total": 105.71198521398424, "count": 64131, "is_parallel": true, "self": 20.529936600961946, "children": { "_process_rank_one_or_two_observation": { "total": 85.18204861302229, "count": 513048, "is_parallel": true, "self": 85.18204861302229 } } } } } } } } } } }, "trainer_advance": { "total": 675.1033306238951, "count": 64132, "self": 2.532060757874433, "children": { "process_trajectory": { "total": 114.78962677301661, "count": 64132, "self": 114.51077737901687, "children": { "RLTrainer._checkpoint": { "total": 0.2788493939997352, "count": 2, "self": 0.2788493939997352 } } }, "_update_policy": { "total": 557.781643093004, "count": 457, "self": 366.945512340038, "children": { "TorchPPOOptimizer.update": { "total": 190.83613075296603, "count": 22818, "self": 190.83613075296603 } } } } } } }, "trainer_threads": { "total": 8.709994290256873e-07, "count": 1, "self": 8.709994290256873e-07 }, "TrainerController._save_models": { "total": 0.09362371200040798, "count": 1, "self": 0.0014217710004231776, "children": { "RLTrainer._checkpoint": { "total": 0.0922019409999848, "count": 1, "self": 0.0922019409999848 } } } } } } }