{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48803627490997314, "min": 0.4691722095012665, "max": 1.326302170753479, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14656.705078125, "min": 14172.75390625, "max": 40234.703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989955.0, "min": 29876.0, "max": 989955.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989955.0, "min": 29876.0, "max": 989955.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4348636865615845, "min": -0.09703798592090607, "max": 0.47636258602142334, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 118.71778869628906, "min": -23.386154174804688, "max": 126.71244812011719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.442028284072876, "min": -1.442028284072876, "max": 0.4942820072174072, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -393.6737060546875, "min": -393.6737060546875, "max": 117.14483642578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06956362520023027, "min": 0.0644105707504917, "max": 0.07259371186792786, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9738907528032238, "min": 0.5020742187254403, "max": 1.0214940445924487, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.4001004337859783, "min": 0.0004993289633673127, "max": 0.4001004337859783, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 5.601406073003696, "min": 0.005991947560407752, "max": 5.601406073003696, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.460240370428571e-06, "min": 7.460240370428571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010444336518599999, "min": 0.00010444336518599999, "max": 0.0032596697134434994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248671428571428, "min": 0.10248671428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348139999999998, "min": 1.3886848, "max": 2.4426158, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584227571428571, "min": 0.0002584227571428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036179185999999997, "min": 0.0036179185999999997, "max": 0.10867699435, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009831900708377361, "min": 0.009785848669707775, "max": 0.483313649892807, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1376466155052185, "min": 0.1370018869638443, "max": 3.383195638656616, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 434.2368421052632, "min": 383.02777777777777, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 33002.0, "min": 16803.0, "max": 33585.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3814815551434692, "min": -0.9999375520274043, "max": 1.5551588819043276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.99259819090366, "min": -31.998001664876938, "max": 113.52659837901592, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3814815551434692, "min": -0.9999375520274043, "max": 1.5551588819043276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.99259819090366, "min": -31.998001664876938, "max": 113.52659837901592, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04368210466991753, "min": 0.03957188677414295, "max": 9.365610009607147, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.319839954913732, "min": 2.8887477345124353, "max": 159.2153701633215, "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": "1682755751", "python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/mlagent_env/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": "1.8.1+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1682757175" }, "total": 1424.1670268690214, "count": 1, "self": 0.373104577884078, "children": { "run_training.setup": { "total": 0.016415647231042385, "count": 1, "self": 0.016415647231042385 }, "TrainerController.start_learning": { "total": 1423.7775066439062, "count": 1, "self": 1.4699603440240026, "children": { "TrainerController._reset_env": { "total": 4.1304948180913925, "count": 1, "self": 4.1304948180913925 }, "TrainerController.advance": { "total": 1418.1123624667525, "count": 63550, "self": 1.4319884749129415, "children": { "env_step": { "total": 985.8177361739799, "count": 63550, "self": 886.8938535535708, "children": { "SubprocessEnvManager._take_step": { "total": 98.04699791874737, "count": 63550, "self": 3.8840013816952705, "children": { "TorchPolicy.evaluate": { "total": 94.1629965370521, "count": 62567, "self": 94.1629965370521 } } }, "workers": { "total": 0.8768847016617656, "count": 63550, "self": 0.0, "children": { "worker_root": { "total": 1421.1386285750195, "count": 63550, "is_parallel": true, "self": 616.0351407621056, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001508898101747036, "count": 1, "is_parallel": true, "self": 0.00047452282160520554, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010343752801418304, "count": 8, "is_parallel": true, "self": 0.0010343752801418304 } } }, "UnityEnvironment.step": { "total": 0.03700953349471092, "count": 1, "is_parallel": true, "self": 0.0003574267029762268, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002939673140645027, "count": 1, "is_parallel": true, "self": 0.0002939673140645027 }, "communicator.exchange": { "total": 0.03551559429615736, "count": 1, "is_parallel": true, "self": 0.03551559429615736 }, "steps_from_proto": { "total": 0.0008425451815128326, "count": 1, "is_parallel": true, "self": 0.0002325214445590973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006100237369537354, "count": 8, "is_parallel": true, "self": 0.0006100237369537354 } } } } } } }, "UnityEnvironment.step": { "total": 805.103487812914, "count": 63549, "is_parallel": true, "self": 16.721625689417124, "children": { "UnityEnvironment._generate_step_input": { "total": 11.140724504366517, "count": 63549, "is_parallel": true, "self": 11.140724504366517 }, "communicator.exchange": { "total": 730.9195039076731, "count": 63549, "is_parallel": true, "self": 730.9195039076731 }, "steps_from_proto": { "total": 46.32163371145725, "count": 63549, "is_parallel": true, "self": 11.537732562981546, "children": { "_process_rank_one_or_two_observation": { "total": 34.78390114847571, "count": 508392, "is_parallel": true, "self": 34.78390114847571 } } } } } } } } } } }, "trainer_advance": { "total": 430.86263781785965, "count": 63550, "self": 2.588444850407541, "children": { "process_trajectory": { "total": 76.32361845392734, "count": 63550, "self": 76.18030210863799, "children": { "RLTrainer._checkpoint": { "total": 0.14331634528934956, "count": 2, "self": 0.14331634528934956 } } }, "_update_policy": { "total": 351.95057451352477, "count": 449, "self": 213.26261940971017, "children": { "TorchPPOOptimizer.update": { "total": 138.6879551038146, "count": 22791, "self": 138.6879551038146 } } } } } } }, "trainer_threads": { "total": 2.039596438407898e-06, "count": 1, "self": 2.039596438407898e-06 }, "TrainerController._save_models": { "total": 0.06468697544187307, "count": 1, "self": 0.0014809630811214447, "children": { "RLTrainer._checkpoint": { "total": 0.06320601236075163, "count": 1, "self": 0.06320601236075163 } } } } } } }