{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7408730387687683, "min": 0.7256978154182434, "max": 1.4059088230133057, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22012.8203125, "min": 21678.044921875, "max": 42649.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08190051466226578, "min": -0.11029922962188721, "max": 0.1130589172244072, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 20.147525787353516, "min": -26.582115173339844, "max": 28.264728546142578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005988653749227524, "min": -0.005988653749227524, "max": 0.2272021472454071, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4732087850570679, "min": -1.4732087850570679, "max": 53.84690856933594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06862332884901194, "min": 0.06351672026971308, "max": 0.07364696889957859, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9607266038861673, "min": 0.48982802991492363, "max": 1.0330682859348599, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008528645520632242, "min": 0.000161567621761852, "max": 0.008958733257410735, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11940103728885137, "min": 0.002067075791322369, "max": 0.13438099886116103, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.646583165457138e-06, "min": 7.646583165457138e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010705216431639993, "min": 0.00010705216431639993, "max": 0.0031441271519577, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254882857142858, "min": 0.10254882857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356836000000002, "min": 1.3886848, "max": 2.3480423, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026462797428571414, "min": 0.00026462797428571414, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003704791639999998, "min": 0.003704791639999998, "max": 0.10482942577, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007577203214168549, "min": 0.007577203214168549, "max": 0.26895540952682495, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10608084499835968, "min": 0.10608084499835968, "max": 1.8826878070831299, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 762.2051282051282, "min": 742.439024390244, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29726.0, "min": 15984.0, "max": 32664.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.2631127859155337, "min": -1.0000000521540642, "max": 0.5256682574385549, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 10.261398650705814, "min": -31.99920167028904, "max": 21.552398554980755, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.2631127859155337, "min": -1.0000000521540642, "max": 0.5256682574385549, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 10.261398650705814, "min": -31.99920167028904, "max": 21.552398554980755, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.060054309810743105, "min": 0.060054309810743105, "max": 5.330888848286122, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.342118082618981, "min": 2.342118082618981, "max": 85.29422157257795, "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": "1692270301", "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": "1692272419" }, "total": 2117.5034729599997, "count": 1, "self": 0.4874810289998095, "children": { "run_training.setup": { "total": 0.06359278600029938, "count": 1, "self": 0.06359278600029938 }, "TrainerController.start_learning": { "total": 2116.9523991449996, "count": 1, "self": 1.3452333810960226, "children": { "TrainerController._reset_env": { "total": 6.48626550400013, "count": 1, "self": 6.48626550400013 }, "TrainerController.advance": { "total": 2109.016387582903, "count": 63175, "self": 1.3950699109063862, "children": { "env_step": { "total": 1446.0760474240046, "count": 63175, "self": 1336.5401860150891, "children": { "SubprocessEnvManager._take_step": { "total": 108.69718923088203, "count": 63175, "self": 4.654513970873268, "children": { "TorchPolicy.evaluate": { "total": 104.04267526000876, "count": 62555, "self": 104.04267526000876 } } }, "workers": { "total": 0.8386721780334483, "count": 63175, "self": 0.0, "children": { "worker_root": { "total": 2112.3840987389763, "count": 63175, "is_parallel": true, "self": 887.9632015380353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002764348999789945, "count": 1, "is_parallel": true, "self": 0.0007742509992567648, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019900980005331803, "count": 8, "is_parallel": true, "self": 0.0019900980005331803 } } }, "UnityEnvironment.step": { "total": 0.09372274599991215, "count": 1, "is_parallel": true, "self": 0.0006201639998835162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005425370000011753, "count": 1, "is_parallel": true, "self": 0.0005425370000011753 }, "communicator.exchange": { "total": 0.09024433200011117, "count": 1, "is_parallel": true, "self": 0.09024433200011117 }, "steps_from_proto": { "total": 0.002315712999916286, "count": 1, "is_parallel": true, "self": 0.0004095479994248308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019061650004914554, "count": 8, "is_parallel": true, "self": 0.0019061650004914554 } } } } } } }, "UnityEnvironment.step": { "total": 1224.420897200941, "count": 63174, "is_parallel": true, "self": 33.890451529978236, "children": { "UnityEnvironment._generate_step_input": { "total": 23.072896974105788, "count": 63174, "is_parallel": true, "self": 23.072896974105788 }, "communicator.exchange": { "total": 1063.0539335889266, "count": 63174, "is_parallel": true, "self": 1063.0539335889266 }, "steps_from_proto": { "total": 104.40361510793036, "count": 63174, "is_parallel": true, "self": 20.32481236993499, "children": { "_process_rank_one_or_two_observation": { "total": 84.07880273799537, "count": 505392, "is_parallel": true, "self": 84.07880273799537 } } } } } } } } } } }, "trainer_advance": { "total": 661.545270247992, "count": 63175, "self": 2.481973563979409, "children": { "process_trajectory": { "total": 108.6138666520169, "count": 63175, "self": 108.38428368001723, "children": { "RLTrainer._checkpoint": { "total": 0.22958297199966182, "count": 2, "self": 0.22958297199966182 } } }, "_update_policy": { "total": 550.4494300319957, "count": 441, "self": 359.19104461902634, "children": { "TorchPPOOptimizer.update": { "total": 191.25838541296935, "count": 22731, "self": 191.25838541296935 } } } } } } }, "trainer_threads": { "total": 8.370006980840117e-07, "count": 1, "self": 8.370006980840117e-07 }, "TrainerController._save_models": { "total": 0.1045118399997591, "count": 1, "self": 0.0013871490000383346, "children": { "RLTrainer._checkpoint": { "total": 0.10312469099972077, "count": 1, "self": 0.10312469099972077 } } } } } } }