{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46165579557418823, "min": 0.46165579557418823, "max": 1.4438221454620361, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13975.244140625, "min": 13924.521484375, "max": 43799.7890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989973.0, "min": 29928.0, "max": 989973.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989973.0, "min": 29928.0, "max": 989973.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.618240475654602, "min": -0.19759468734264374, "max": 0.618240475654602, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.1985321044922, "min": -46.82994079589844, "max": 176.1985321044922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01467522419989109, "min": -0.0504487082362175, "max": 0.3410690724849701, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.182438850402832, "min": -12.612176895141602, "max": 82.19764709472656, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06757753466444119, "min": 0.0650555044826534, "max": 0.07531298675034956, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9460854853021766, "min": 0.48097637014553196, "max": 1.0976017205102835, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014768230875812017, "min": 0.0007413514506228313, "max": 0.016588016223083278, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20675523226136824, "min": 0.010378920308719638, "max": 0.2488202433462492, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.253754724971427e-06, "min": 7.253754724971427e-06, "max": 0.00029523394444582856, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010155256614959997, "min": 0.00010155256614959997, "max": 0.0036322645892451996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241788571428571, "min": 0.10241788571428571, "max": 0.19841131428571426, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338504, "min": 1.3888791999999999, "max": 2.6107548, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025154678285714283, "min": 0.00025154678285714283, "max": 0.009841290297142856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00352165496, "min": 0.00352165496, "max": 0.12109440452000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011843138374388218, "min": 0.011843138374388218, "max": 0.5239995121955872, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1658039391040802, "min": 0.1658039391040802, "max": 3.667996644973755, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.47872340425533, "min": 294.47872340425533, "max": 992.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27681.0, "min": 16599.0, "max": 32243.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7059789315650338, "min": -0.8677063011564314, "max": 1.7059789315650338, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.0679984986782, "min": -28.273601770401, "max": 165.08299835026264, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7059789315650338, "min": -0.8677063011564314, "max": 1.7059789315650338, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.0679984986782, "min": -28.273601770401, "max": 165.08299835026264, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03613186541770119, "min": 0.03613186541770119, "max": 9.697137282175177, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4325272146816133, "min": 3.4325272146816133, "max": 164.851333796978, "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": "1713720014", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713722186" }, "total": 2171.542801079, "count": 1, "self": 0.8780618380001215, "children": { "run_training.setup": { "total": 0.04486124400000335, "count": 1, "self": 0.04486124400000335 }, "TrainerController.start_learning": { "total": 2170.619877997, "count": 1, "self": 1.7395002469861538, "children": { "TrainerController._reset_env": { "total": 2.1644791970000483, "count": 1, "self": 2.1644791970000483 }, "TrainerController.advance": { "total": 2166.6068785320135, "count": 63889, "self": 1.8939756769882479, "children": { "env_step": { "total": 1460.3876735180354, "count": 63889, "self": 1341.2771155020112, "children": { "SubprocessEnvManager._take_step": { "total": 117.9739057519871, "count": 63889, "self": 4.470343421028531, "children": { "TorchPolicy.evaluate": { "total": 113.50356233095857, "count": 62558, "self": 113.50356233095857 } } }, "workers": { "total": 1.1366522640370817, "count": 63889, "self": 0.0, "children": { "worker_root": { "total": 2166.65908952502, "count": 63889, "is_parallel": true, "self": 950.7275624980227, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006299468999998226, "count": 1, "is_parallel": true, "self": 0.003081528999928196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032179400000700298, "count": 8, "is_parallel": true, "self": 0.0032179400000700298 } } }, "UnityEnvironment.step": { "total": 0.042284953999967456, "count": 1, "is_parallel": true, "self": 0.0005700389999105937, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043862000001126944, "count": 1, "is_parallel": true, "self": 0.00043862000001126944 }, "communicator.exchange": { "total": 0.0398655950000375, "count": 1, "is_parallel": true, "self": 0.0398655950000375 }, "steps_from_proto": { "total": 0.0014107000000080916, "count": 1, "is_parallel": true, "self": 0.00029277100009039714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011179289999176945, "count": 8, "is_parallel": true, "self": 0.0011179289999176945 } } } } } } }, "UnityEnvironment.step": { "total": 1215.9315270269974, "count": 63888, "is_parallel": true, "self": 36.85755013992639, "children": { "UnityEnvironment._generate_step_input": { "total": 18.969451179998885, "count": 63888, "is_parallel": true, "self": 18.969451179998885 }, "communicator.exchange": { "total": 1066.5555063650193, "count": 63888, "is_parallel": true, "self": 1066.5555063650193 }, "steps_from_proto": { "total": 93.54901934205287, "count": 63888, "is_parallel": true, "self": 19.784483338020607, "children": { "_process_rank_one_or_two_observation": { "total": 73.76453600403227, "count": 511104, "is_parallel": true, "self": 73.76453600403227 } } } } } } } } } } }, "trainer_advance": { "total": 704.3252293369897, "count": 63889, "self": 3.4192386629981684, "children": { "process_trajectory": { "total": 119.6919217289921, "count": 63889, "self": 119.4966711559918, "children": { "RLTrainer._checkpoint": { "total": 0.19525057300029403, "count": 2, "self": 0.19525057300029403 } } }, "_update_policy": { "total": 581.2140689449994, "count": 453, "self": 236.18842300199657, "children": { "TorchPPOOptimizer.update": { "total": 345.02564594300287, "count": 22770, "self": 345.02564594300287 } } } } } } }, "trainer_threads": { "total": 1.5400000847876072e-06, "count": 1, "self": 1.5400000847876072e-06 }, "TrainerController._save_models": { "total": 0.10901848100002098, "count": 1, "self": 0.004576508999889484, "children": { "RLTrainer._checkpoint": { "total": 0.1044419720001315, "count": 1, "self": 0.1044419720001315 } } } } } } }