{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.554614245891571, "min": 0.554614245891571, "max": 1.4260224103927612, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16798.15625, "min": 16788.275390625, "max": 43259.81640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989909.0, "min": 29952.0, "max": 989909.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2950536012649536, "min": -0.15915177762508392, "max": 0.36907923221588135, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.00898742675781, "min": -37.718971252441406, "max": 96.69876098632812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010432804003357887, "min": -0.010376200079917908, "max": 0.40074753761291504, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.722961902618408, "min": -2.718564510345459, "max": 94.97716522216797, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06734847385918588, "min": 0.06562924177851528, "max": 0.07408862987055125, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9428786340286024, "min": 0.47354521925160364, "max": 1.045554160236326, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013136212317303511, "min": 0.00010069658054463667, "max": 0.015065520607164047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18390697244224916, "min": 0.0013090555470802766, "max": 0.2259828091074607, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.483254648471435e-06, "min": 7.483254648471435e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010476556507860009, "min": 0.00010476556507860009, "max": 0.0032607734130755996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249438571428574, "min": 0.10249438571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349214000000003, "min": 1.3691136000000002, "max": 2.3869244000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002591891328571431, "min": 0.0002591891328571431, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003628647860000003, "min": 0.003628647860000003, "max": 0.10871374756000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0089903948828578, "min": 0.0089903948828578, "max": 0.42562243342399597, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12586553394794464, "min": 0.12586553394794464, "max": 2.9793570041656494, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 538.1964285714286, "min": 467.55555555555554, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30139.0, "min": 15984.0, "max": 32593.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.211728540382215, "min": -1.0000000521540642, "max": 1.310062038744318, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.85679826140404, "min": -32.000001668930054, "max": 83.2825983390212, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.211728540382215, "min": -1.0000000521540642, "max": 1.310062038744318, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.85679826140404, "min": -32.000001668930054, "max": 83.2825983390212, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.050225450741501323, "min": 0.04660296856610362, "max": 8.722021429799497, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8126252415240742, "min": 2.7029721768340096, "max": 139.55234287679195, "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": "1696322880", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696325135" }, "total": 2254.803126314, "count": 1, "self": 0.5483680030001779, "children": { "run_training.setup": { "total": 0.07177569800001038, "count": 1, "self": 0.07177569800001038 }, "TrainerController.start_learning": { "total": 2254.182982613, "count": 1, "self": 1.5137958089540007, "children": { "TrainerController._reset_env": { "total": 4.786208719000001, "count": 1, "self": 4.786208719000001 }, "TrainerController.advance": { "total": 2247.780510038046, "count": 63374, "self": 1.5653236510170245, "children": { "env_step": { "total": 1577.2473999990368, "count": 63374, "self": 1456.4432850620174, "children": { "SubprocessEnvManager._take_step": { "total": 119.86059675898252, "count": 63374, "self": 5.1189006239523565, "children": { "TorchPolicy.evaluate": { "total": 114.74169613503017, "count": 62555, "self": 114.74169613503017 } } }, "workers": { "total": 0.9435181780368112, "count": 63374, "self": 0.0, "children": { "worker_root": { "total": 2248.9741786539926, "count": 63374, "is_parallel": true, "self": 916.4328524189896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005430153000020255, "count": 1, "is_parallel": true, "self": 0.003978063000147358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014520899998728964, "count": 8, "is_parallel": true, "self": 0.0014520899998728964 } } }, "UnityEnvironment.step": { "total": 0.051286166000011235, "count": 1, "is_parallel": true, "self": 0.0006039249999503227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004859020000367309, "count": 1, "is_parallel": true, "self": 0.0004859020000367309 }, "communicator.exchange": { "total": 0.047301767000021755, "count": 1, "is_parallel": true, "self": 0.047301767000021755 }, "steps_from_proto": { "total": 0.0028945720000024266, "count": 1, "is_parallel": true, "self": 0.0004099140000448642, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024846579999575624, "count": 8, "is_parallel": true, "self": 0.0024846579999575624 } } } } } } }, "UnityEnvironment.step": { "total": 1332.541326235003, "count": 63373, "is_parallel": true, "self": 35.40435709996791, "children": { "UnityEnvironment._generate_step_input": { "total": 23.25160455406086, "count": 63373, "is_parallel": true, "self": 23.25160455406086 }, "communicator.exchange": { "total": 1165.6199731990025, "count": 63373, "is_parallel": true, "self": 1165.6199731990025 }, "steps_from_proto": { "total": 108.26539138197165, "count": 63373, "is_parallel": true, "self": 21.80263735988501, "children": { "_process_rank_one_or_two_observation": { "total": 86.46275402208664, "count": 506984, "is_parallel": true, "self": 86.46275402208664 } } } } } } } } } } }, "trainer_advance": { "total": 668.9677863879922, "count": 63374, "self": 2.86011746801546, "children": { "process_trajectory": { "total": 112.71176032197792, "count": 63374, "self": 112.49109712397791, "children": { "RLTrainer._checkpoint": { "total": 0.2206631980000111, "count": 2, "self": 0.2206631980000111 } } }, "_update_policy": { "total": 553.3959085979989, "count": 436, "self": 359.06787938397827, "children": { "TorchPPOOptimizer.update": { "total": 194.3280292140206, "count": 22845, "self": 194.3280292140206 } } } } } } }, "trainer_threads": { "total": 1.4229999578674324e-06, "count": 1, "self": 1.4229999578674324e-06 }, "TrainerController._save_models": { "total": 0.10246662400004425, "count": 1, "self": 0.001532281999971019, "children": { "RLTrainer._checkpoint": { "total": 0.10093434200007323, "count": 1, "self": 0.10093434200007323 } } } } } } }