{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2997552752494812, "min": 0.2997552752494812, "max": 1.5152795314788818, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9107.7646484375, "min": 9107.7646484375, "max": 45967.51953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7014755010604858, "min": -0.09194272011518478, "max": 0.7432578206062317, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 204.12937927246094, "min": -22.066253662109375, "max": 218.26365661621094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03070581518113613, "min": 0.001341871335171163, "max": 0.49201515316963196, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.935392379760742, "min": 0.3663308620452881, "max": 116.60758972167969, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06820201376588861, "min": 0.06280537999907825, "max": 0.07166925977860251, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9548281927224405, "min": 0.49095686052654247, "max": 1.068701341864653, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01461417185644331, "min": 0.000261157787600734, "max": 0.01788240953285641, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20459840599020634, "min": 0.003395051238809542, "max": 0.25035373345998974, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.593161754692857e-06, "min": 7.593161754692857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001063042645657, "min": 0.0001063042645657, "max": 0.0036335212888262995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253102142857144, "min": 0.10253102142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354343000000003, "min": 1.3886848, "max": 2.61773, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002628490407142857, "min": 0.0002628490407142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036798865699999997, "min": 0.0036798865699999997, "max": 0.12113625263, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013298647478222847, "min": 0.013298647478222847, "max": 0.40662500262260437, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18618106842041016, "min": 0.18618106842041016, "max": 2.846374988555908, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 270.5217391304348, "min": 257.5701754385965, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31110.0, "min": 15984.0, "max": 33444.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.694688686080601, "min": -1.0000000521540642, "max": 1.7424298067364776, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 194.8891988992691, "min": -30.50660166144371, "max": 198.63699796795845, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.694688686080601, "min": -1.0000000521540642, "max": 1.7424298067364776, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 194.8891988992691, "min": -30.50660166144371, "max": 198.63699796795845, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03703352345973658, "min": 0.036862659776504686, "max": 8.539628577418625, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.258855197869707, "min": 4.202343214521534, "max": 136.634057238698, "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": "1792016792", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/mlagents-python310/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1792019392" }, "total": 2599.410241235, "count": 1, "self": 0.5307266829995569, "children": { "run_training.setup": { "total": 0.016464518000248063, "count": 1, "self": 0.016464518000248063 }, "TrainerController.start_learning": { "total": 2598.863050034, "count": 1, "self": 1.6543815970953801, "children": { "TrainerController._reset_env": { "total": 1.892956703999971, "count": 1, "self": 1.892956703999971 }, "TrainerController.advance": { "total": 2595.223503116904, "count": 64411, "self": 1.694384649998483, "children": { "env_step": { "total": 1857.8451215179198, "count": 64411, "self": 1684.9659631611153, "children": { "SubprocessEnvManager._take_step": { "total": 171.8381904098801, "count": 64411, "self": 5.332296191789737, "children": { "TorchPolicy.evaluate": { "total": 166.50589421809036, "count": 62567, "self": 166.50589421809036 } } }, "workers": { "total": 1.040967946924411, "count": 64411, "self": 0.0, "children": { "worker_root": { "total": 2595.8077803678984, "count": 64411, "is_parallel": true, "self": 1039.3021312238857, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002202989000124944, "count": 1, "is_parallel": true, "self": 0.0007418100012728246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014611789988521195, "count": 8, "is_parallel": true, "self": 0.0014611789988521195 } } }, "UnityEnvironment.step": { "total": 0.055944055000054504, "count": 1, "is_parallel": true, "self": 0.0006054890000086743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005638040001940681, "count": 1, "is_parallel": true, "self": 0.0005638040001940681 }, "communicator.exchange": { "total": 0.05289042300000801, "count": 1, "is_parallel": true, "self": 0.05289042300000801 }, "steps_from_proto": { "total": 0.0018843389998437488, "count": 1, "is_parallel": true, "self": 0.00039330299932771595, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014910360005160328, "count": 8, "is_parallel": true, "self": 0.0014910360005160328 } } } } } } }, "UnityEnvironment.step": { "total": 1556.5056491440128, "count": 64410, "is_parallel": true, "self": 37.7787999229422, "children": { "UnityEnvironment._generate_step_input": { "total": 26.75833485304429, "count": 64410, "is_parallel": true, "self": 26.75833485304429 }, "communicator.exchange": { "total": 1374.1525249109363, "count": 64410, "is_parallel": true, "self": 1374.1525249109363 }, "steps_from_proto": { "total": 117.81598945708993, "count": 64410, "is_parallel": true, "self": 25.43061598423583, "children": { "_process_rank_one_or_two_observation": { "total": 92.3853734728541, "count": 515280, "is_parallel": true, "self": 92.3853734728541 } } } } } } } } } } }, "trainer_advance": { "total": 735.6839969489856, "count": 64411, "self": 3.1019879731320543, "children": { "process_trajectory": { "total": 145.65794454285424, "count": 64411, "self": 145.43942882385454, "children": { "RLTrainer._checkpoint": { "total": 0.21851571899969713, "count": 2, "self": 0.21851571899969713 } } }, "_update_policy": { "total": 586.9240644329993, "count": 456, "self": 325.17263264803387, "children": { "TorchPPOOptimizer.update": { "total": 261.75143178496546, "count": 22803, "self": 261.75143178496546 } } } } } } }, "trainer_threads": { "total": 1.2820000847568735e-06, "count": 1, "self": 1.2820000847568735e-06 }, "TrainerController._save_models": { "total": 0.09220733400070458, "count": 1, "self": 0.0011102320004283683, "children": { "RLTrainer._checkpoint": { "total": 0.09109710200027621, "count": 1, "self": 0.09109710200027621 } } } } } } }