{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36924877762794495, "min": 0.36924877762794495, "max": 1.4523899555206299, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11160.1748046875, "min": 11099.6796875, "max": 44059.703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989998.0, "min": 29952.0, "max": 989998.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5812302827835083, "min": -0.10208908468484879, "max": 0.6132251024246216, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.58201599121094, "min": -24.603469848632812, "max": 173.54270935058594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 3.2994329929351807, "min": -0.0751885399222374, "max": 3.2994329929351807, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 917.2423706054688, "min": -20.827224731445312, "max": 917.2423706054688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0708113071277261, "min": 0.06422742932461135, "max": 0.0732920232287387, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9913582997881654, "min": 0.48411869179058004, "max": 1.0544001057831909, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.5004773908072994, "min": 0.0003111687279707699, "max": 0.5375925393857282, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 7.006683471302192, "min": 0.004356362191590779, "max": 7.526295551400194, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.558983194657138e-06, "min": 7.558983194657138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010582576472519994, "min": 0.00010582576472519994, "max": 0.003507378230874, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251962857142857, "min": 0.10251962857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352748, "min": 1.3691136000000002, "max": 2.569126, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002617108942857142, "min": 0.0002617108942857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036639525199999986, "min": 0.0036639525199999986, "max": 0.11693568739999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011942843906581402, "min": 0.011770850047469139, "max": 0.3961154520511627, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16719982028007507, "min": 0.16479189693927765, "max": 2.772808074951172, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.8709677419355, "min": 325.8709677419355, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30306.0, "min": 15984.0, "max": 32541.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6305412825035013, "min": -1.0000000521540642, "max": 1.6496110926899645, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 150.0097979903221, "min": -32.000001668930054, "max": 151.38479866087437, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6305412825035013, "min": -1.0000000521540642, "max": 1.6496110926899645, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 150.0097979903221, "min": -32.000001668930054, "max": 151.38479866087437, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03992541726335691, "min": 0.03992541726335691, "max": 7.361367178149521, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6731383882288355, "min": 3.6364120286307298, "max": 117.78187485039234, "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": "1792338543", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/mla/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1792342808" }, "total": 4264.642719308, "count": 1, "self": 0.7407196559997828, "children": { "run_training.setup": { "total": 0.03595554200001061, "count": 1, "self": 0.03595554200001061 }, "TrainerController.start_learning": { "total": 4263.86604411, "count": 1, "self": 2.6817127620915926, "children": { "TrainerController._reset_env": { "total": 3.9922463380000863, "count": 1, "self": 3.9922463380000863 }, "TrainerController.advance": { "total": 4257.120470833909, "count": 63886, "self": 2.462334975045451, "children": { "env_step": { "total": 3099.9750518579613, "count": 63886, "self": 2928.479594648938, "children": { "SubprocessEnvManager._take_step": { "total": 169.79125025901976, "count": 63886, "self": 7.477867909963834, "children": { "TorchPolicy.evaluate": { "total": 162.31338234905593, "count": 62569, "self": 162.31338234905593 } } }, "workers": { "total": 1.7042069500034813, "count": 63886, "self": 0.0, "children": { "worker_root": { "total": 4254.320214495901, "count": 63886, "is_parallel": true, "self": 1535.5840115099045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005011772999978348, "count": 1, "is_parallel": true, "self": 0.0016293710002628359, "children": { "_process_rank_one_or_two_observation": { "total": 0.003382401999715512, "count": 8, "is_parallel": true, "self": 0.003382401999715512 } } }, "UnityEnvironment.step": { "total": 0.06995126400011031, "count": 1, "is_parallel": true, "self": 0.0007827800002360163, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006150359999992361, "count": 1, "is_parallel": true, "self": 0.0006150359999992361 }, "communicator.exchange": { "total": 0.0662645639999937, "count": 1, "is_parallel": true, "self": 0.0662645639999937 }, "steps_from_proto": { "total": 0.0022888839998813637, "count": 1, "is_parallel": true, "self": 0.0005465409999487747, "children": { "_process_rank_one_or_two_observation": { "total": 0.001742342999932589, "count": 8, "is_parallel": true, "self": 0.001742342999932589 } } } } } } }, "UnityEnvironment.step": { "total": 2718.736202985997, "count": 63885, "is_parallel": true, "self": 54.837408258948926, "children": { "UnityEnvironment._generate_step_input": { "total": 37.360175172113486, "count": 63885, "is_parallel": true, "self": 37.360175172113486 }, "communicator.exchange": { "total": 2461.9023238579393, "count": 63885, "is_parallel": true, "self": 2461.9023238579393 }, "steps_from_proto": { "total": 164.63629569699538, "count": 63885, "is_parallel": true, "self": 34.64490468944177, "children": { "_process_rank_one_or_two_observation": { "total": 129.9913910075536, "count": 511080, "is_parallel": true, "self": 129.9913910075536 } } } } } } } } } } }, "trainer_advance": { "total": 1154.6830840009022, "count": 63886, "self": 4.6378392178769445, "children": { "process_trajectory": { "total": 166.93139961402062, "count": 63886, "self": 166.6409801500206, "children": { "RLTrainer._checkpoint": { "total": 0.29041946400002416, "count": 2, "self": 0.29041946400002416 } } }, "_update_policy": { "total": 983.1138451690047, "count": 448, "self": 398.9246071489624, "children": { "TorchPPOOptimizer.update": { "total": 584.1892380200422, "count": 22827, "self": 584.1892380200422 } } } } } } }, "trainer_threads": { "total": 1.4830002328380942e-06, "count": 1, "self": 1.4830002328380942e-06 }, "TrainerController._save_models": { "total": 0.07161269299922424, "count": 1, "self": 0.0017469479998908355, "children": { "RLTrainer._checkpoint": { "total": 0.0698657449993334, "count": 1, "self": 0.0698657449993334 } } } } } } }