{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4191916286945343, "min": 0.4191916286945343, "max": 1.4041160345077515, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 12548.9208984375, "min": 12548.9208984375, "max": 42595.265625, "count": 35 }, "Pyramids.Step.mean": { "value": 1049922.0, "min": 29951.0, "max": 1049922.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049922.0, "min": 29951.0, "max": 1049922.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.49225252866744995, "min": -0.1551201343536377, "max": 0.6096478700637817, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 131.92367553710938, "min": -36.76347351074219, "max": 170.0917510986328, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006229468155652285, "min": 0.000626862165518105, "max": 0.357185035943985, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.6694974899291992, "min": 0.16925278306007385, "max": 84.6528549194336, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07229101247421899, "min": 0.0651472116864863, "max": 0.07564171897839293, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0120741746390658, "min": 0.4903245060457098, "max": 1.0948472069719049, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014379626243145833, "min": 7.11517913249452e-05, "max": 0.015148568557141967, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20131476740404167, "min": 0.0009249732872242875, "max": 0.2219896464569805, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019647628450791666, "min": 0.00019647628450791666, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027506679831108332, "min": 0.0020886848037717336, "max": 0.003969293876902066, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16549208333333335, "min": 0.16549208333333335, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.316889166666667, "min": 1.3962282666666668, "max": 2.7230979333333334, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006552659125, "min": 0.006552659125, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09173722775, "min": 0.06962320384, "max": 0.13231748354, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008201309479773045, "min": 0.007737783249467611, "max": 0.40679264068603516, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11481833457946777, "min": 0.10832896828651428, "max": 2.847548484802246, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.7710843373494, "min": 345.40909090909093, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29944.0, "min": 16878.0, "max": 32509.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5187252835336937, "min": -0.9999742459866309, "max": 1.65459089031951, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.05419853329659, "min": -30.999201625585556, "max": 145.60399834811687, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5187252835336937, "min": -0.9999742459866309, "max": 1.65459089031951, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.05419853329659, "min": -30.999201625585556, "max": 145.60399834811687, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030416918922698193, "min": 0.028324216204816555, "max": 8.233933187582913, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 2.52460427058395, "min": 2.335729565442307, "max": 139.97686418890953, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1776524019", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/miniconda/envs/mlagents310/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1776526623" }, "total": 2603.8554895120005, "count": 1, "self": 0.4853375520001464, "children": { "run_training.setup": { "total": 0.022020620000148483, "count": 1, "self": 0.022020620000148483 }, "TrainerController.start_learning": { "total": 2603.3481313400002, "count": 1, "self": 1.624651873921266, "children": { "TrainerController._reset_env": { "total": 2.2136162229999172, "count": 1, "self": 2.2136162229999172 }, "TrainerController.advance": { "total": 2599.5098202580793, "count": 67472, "self": 1.6200794561614202, "children": { "env_step": { "total": 1836.4519524099273, "count": 67472, "self": 1656.7595589478456, "children": { "SubprocessEnvManager._take_step": { "total": 178.69033358103025, "count": 67472, "self": 5.467433303009784, "children": { "TorchPolicy.evaluate": { "total": 173.22290027802046, "count": 66406, "self": 173.22290027802046 } } }, "workers": { "total": 1.0020598810515366, "count": 67471, "self": 0.0, "children": { "worker_root": { "total": 2596.4326845661226, "count": 67471, "is_parallel": true, "self": 1077.5683324820443, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001817084000322211, "count": 1, "is_parallel": true, "self": 0.0006131320001259155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012039520001962956, "count": 8, "is_parallel": true, "self": 0.0012039520001962956 } } }, "UnityEnvironment.step": { "total": 0.062458886000058556, "count": 1, "is_parallel": true, "self": 0.0007014469997557171, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004954080000061367, "count": 1, "is_parallel": true, "self": 0.0004954080000061367 }, "communicator.exchange": { "total": 0.05917248400010067, "count": 1, "is_parallel": true, "self": 0.05917248400010067 }, "steps_from_proto": { "total": 0.002089547000196035, "count": 1, "is_parallel": true, "self": 0.0004098670001440041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016796800000520307, "count": 8, "is_parallel": true, "self": 0.0016796800000520307 } } } } } } }, "UnityEnvironment.step": { "total": 1518.8643520840783, "count": 67470, "is_parallel": true, "self": 39.511155604115174, "children": { "UnityEnvironment._generate_step_input": { "total": 27.881286567982443, "count": 67470, "is_parallel": true, "self": 27.881286567982443 }, "communicator.exchange": { "total": 1320.759749429948, "count": 67470, "is_parallel": true, "self": 1320.759749429948 }, "steps_from_proto": { "total": 130.7121604820327, "count": 67470, "is_parallel": true, "self": 26.857648270737172, "children": { "_process_rank_one_or_two_observation": { "total": 103.85451221129551, "count": 539760, "is_parallel": true, "self": 103.85451221129551 } } } } } } } } } } }, "trainer_advance": { "total": 761.4377883919906, "count": 67471, "self": 3.0851175460652485, "children": { "process_trajectory": { "total": 147.17739018092152, "count": 67471, "self": 146.9719963919215, "children": { "RLTrainer._checkpoint": { "total": 0.20539378900002703, "count": 2, "self": 0.20539378900002703 } } }, "_update_policy": { "total": 611.1752806650038, "count": 477, "self": 339.84343691800404, "children": { "TorchPPOOptimizer.update": { "total": 271.33184374699977, "count": 24189, "self": 271.33184374699977 } } } } } } }, "trainer_threads": { "total": 1.419000000169035e-06, "count": 1, "self": 1.419000000169035e-06 }, "TrainerController._save_models": { "total": 4.15659997088369e-05, "count": 1, "self": 2.315199890290387e-05, "children": { "RLTrainer._checkpoint": { "total": 1.841400080593303e-05, "count": 1, "self": 1.841400080593303e-05 } } } } } } }