{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38729771971702576, "min": 0.3853414058685303, "max": 1.3900351524353027, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11470.208984375, "min": 11399.9404296875, "max": 42168.10546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5025095343589783, "min": -0.10628219693899155, "max": 0.5982186794281006, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 136.18008422851562, "min": -25.614009857177734, "max": 166.30479431152344, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008587466552853584, "min": -0.00292215496301651, "max": 0.44154250621795654, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3272035121917725, "min": -0.7919039726257324, "max": 104.64557647705078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07042836474994103, "min": 0.06463789745092592, "max": 0.07465106075978838, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9859971064991745, "min": 0.4973175405287492, "max": 1.1197659113968257, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01439024162530023, "min": 0.00019515904372693473, "max": 0.016481910407438755, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20146338275420322, "min": 0.002341908524723217, "max": 0.2457869820160947, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.71258314345714e-06, "min": 7.71258314345714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010797616400839996, "min": 0.00010797616400839996, "max": 0.0032249629250124, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257082857142859, "min": 0.10257082857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359916000000001, "min": 1.3886848, "max": 2.3176271999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026682577428571426, "min": 0.00026682577428571426, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037355608399999994, "min": 0.0037355608399999994, "max": 0.10751126124000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00984563585370779, "min": 0.00984563585370779, "max": 0.4996545910835266, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13783890008926392, "min": 0.13783890008926392, "max": 3.497582197189331, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 395.46153846153845, "min": 323.31111111111113, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30846.0, "min": 15984.0, "max": 32297.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4295417528740968, "min": -1.0000000521540642, "max": 1.6322333147128423, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.93379847705364, "min": -31.998401671648026, "max": 146.9009983241558, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4295417528740968, "min": -1.0000000521540642, "max": 1.6322333147128423, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.93379847705364, "min": -31.998401671648026, "max": 146.9009983241558, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039737957967754714, "min": 0.0360181934740265, "max": 9.992280322127044, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1392986794526223, "min": 3.1346675031236373, "max": 159.8764851540327, "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": "1739062090", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id={PYARAMID_RUN_ID} --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739065477" }, "total": 3386.905189491, "count": 1, "self": 0.6986803169997984, "children": { "run_training.setup": { "total": 0.028693217000068216, "count": 1, "self": 0.028693217000068216 }, "TrainerController.start_learning": { "total": 3386.177815957, "count": 1, "self": 2.3784632969682207, "children": { "TrainerController._reset_env": { "total": 3.4407767619999277, "count": 1, "self": 3.4407767619999277 }, "TrainerController.advance": { "total": 3380.271053250032, "count": 63713, "self": 2.553238244053773, "children": { "env_step": { "total": 2248.3026288589876, "count": 63713, "self": 2076.2170634709446, "children": { "SubprocessEnvManager._take_step": { "total": 170.6862976220459, "count": 63713, "self": 7.384994348035889, "children": { "TorchPolicy.evaluate": { "total": 163.30130327401002, "count": 62550, "self": 163.30130327401002 } } }, "workers": { "total": 1.3992677659969104, "count": 63713, "self": 0.0, "children": { "worker_root": { "total": 3378.145833700032, "count": 63713, "is_parallel": true, "self": 1485.3943185409953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005820688999961021, "count": 1, "is_parallel": true, "self": 0.004089155000087885, "children": { "_process_rank_one_or_two_observation": { "total": 0.001731533999873136, "count": 8, "is_parallel": true, "self": 0.001731533999873136 } } }, "UnityEnvironment.step": { "total": 0.0637089049999986, "count": 1, "is_parallel": true, "self": 0.0007021860000122615, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005613700000139943, "count": 1, "is_parallel": true, "self": 0.0005613700000139943 }, "communicator.exchange": { "total": 0.0603707120000081, "count": 1, "is_parallel": true, "self": 0.0603707120000081 }, "steps_from_proto": { "total": 0.002074636999964241, "count": 1, "is_parallel": true, "self": 0.0006135500000254979, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014610869999387432, "count": 8, "is_parallel": true, "self": 0.0014610869999387432 } } } } } } }, "UnityEnvironment.step": { "total": 1892.751515159037, "count": 63712, "is_parallel": true, "self": 47.48118881803293, "children": { "UnityEnvironment._generate_step_input": { "total": 30.854301166966593, "count": 63712, "is_parallel": true, "self": 30.854301166966593 }, "communicator.exchange": { "total": 1686.2732888519913, "count": 63712, "is_parallel": true, "self": 1686.2732888519913 }, "steps_from_proto": { "total": 128.14273632204583, "count": 63712, "is_parallel": true, "self": 27.797276882953838, "children": { "_process_rank_one_or_two_observation": { "total": 100.345459439092, "count": 509696, "is_parallel": true, "self": 100.345459439092 } } } } } } } } } } }, "trainer_advance": { "total": 1129.4151861469902, "count": 63713, "self": 4.574359873966614, "children": { "process_trajectory": { "total": 167.2293419900226, "count": 63713, "self": 166.81339157402238, "children": { "RLTrainer._checkpoint": { "total": 0.4159504160002143, "count": 2, "self": 0.4159504160002143 } } }, "_update_policy": { "total": 957.611484283001, "count": 440, "self": 373.78398477501935, "children": { "TorchPPOOptimizer.update": { "total": 583.8274995079817, "count": 22845, "self": 583.8274995079817 } } } } } } }, "trainer_threads": { "total": 9.319996934209485e-07, "count": 1, "self": 9.319996934209485e-07 }, "TrainerController._save_models": { "total": 0.08752171600008296, "count": 1, "self": 0.0022351530001287756, "children": { "RLTrainer._checkpoint": { "total": 0.08528656299995419, "count": 1, "self": 0.08528656299995419 } } } } } } }