{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44333556294441223, "min": 0.44333556294441223, "max": 1.472771167755127, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13356.8134765625, "min": 13356.8134765625, "max": 44677.984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41269513964653015, "min": -0.10084386169910431, "max": 0.5040339827537537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 110.602294921875, "min": -24.50505828857422, "max": 136.08917236328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011449173092842102, "min": 0.0027964459732174873, "max": 0.28954175114631653, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.068378448486328, "min": 0.7438546419143677, "max": 70.06910705566406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06872427021687248, "min": 0.06548714281417853, "max": 0.07335195838593593, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9621397830362148, "min": 0.5134637087015516, "max": 1.0775599155458624, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013862146865993089, "min": 9.50651283589899e-05, "max": 0.014600543580541364, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19407005612390324, "min": 0.0013309117970258587, "max": 0.2044076101275791, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.255983295657143e-06, "min": 7.255983295657143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010158376613920001, "min": 0.00010158376613920001, "max": 0.0034911718362760995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241862857142857, "min": 0.10241862857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338608, "min": 1.3886848, "max": 2.5272417, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025162099428571434, "min": 0.00025162099428571434, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035226939200000006, "min": 0.0035226939200000006, "max": 0.11638601761, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015034322626888752, "min": 0.015034322626888752, "max": 0.43708381056785583, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21048051118850708, "min": 0.21048051118850708, "max": 3.059586763381958, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 432.37142857142857, "min": 376.57894736842104, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30266.0, "min": 15984.0, "max": 32901.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4247256875038148, "min": -1.0000000521540642, "max": 1.5181157708560165, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.73079812526703, "min": -31.990801632404327, "max": 115.37679858505726, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4247256875038148, "min": -1.0000000521540642, "max": 1.5181157708560165, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.73079812526703, "min": -31.990801632404327, "max": 115.37679858505726, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06680355076345482, "min": 0.060294906398332, "max": 9.192445791326463, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.676248553441837, "min": 4.582412886273232, "max": 147.0791326612234, "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": "1731166517", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731168661" }, "total": 2143.9791966740004, "count": 1, "self": 0.4889524930003972, "children": { "run_training.setup": { "total": 0.06411676600009741, "count": 1, "self": 0.06411676600009741 }, "TrainerController.start_learning": { "total": 2143.426127415, "count": 1, "self": 1.2974517660341007, "children": { "TrainerController._reset_env": { "total": 2.1013219589999608, "count": 1, "self": 2.1013219589999608 }, "TrainerController.advance": { "total": 2139.9447431379663, "count": 63541, "self": 1.3256756559871974, "children": { "env_step": { "total": 1457.9661251070033, "count": 63541, "self": 1313.8727548150464, "children": { "SubprocessEnvManager._take_step": { "total": 143.30890784196527, "count": 63541, "self": 4.5357571730041855, "children": { "TorchPolicy.evaluate": { "total": 138.77315066896108, "count": 62558, "self": 138.77315066896108 } } }, "workers": { "total": 0.784462449991679, "count": 63541, "self": 0.0, "children": { "worker_root": { "total": 2138.966579962926, "count": 63541, "is_parallel": true, "self": 936.4441861968796, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002077177000046504, "count": 1, "is_parallel": true, "self": 0.0006540309998399607, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014231460002065432, "count": 8, "is_parallel": true, "self": 0.0014231460002065432 } } }, "UnityEnvironment.step": { "total": 0.04911290800009738, "count": 1, "is_parallel": true, "self": 0.0006603369999993447, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045882900008109573, "count": 1, "is_parallel": true, "self": 0.00045882900008109573 }, "communicator.exchange": { "total": 0.04619749199991929, "count": 1, "is_parallel": true, "self": 0.04619749199991929 }, "steps_from_proto": { "total": 0.0017962500000976434, "count": 1, "is_parallel": true, "self": 0.00037439599987010297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014218540002275404, "count": 8, "is_parallel": true, "self": 0.0014218540002275404 } } } } } } }, "UnityEnvironment.step": { "total": 1202.5223937660464, "count": 63540, "is_parallel": true, "self": 32.54284499311575, "children": { "UnityEnvironment._generate_step_input": { "total": 23.49602115497487, "count": 63540, "is_parallel": true, "self": 23.49602115497487 }, "communicator.exchange": { "total": 1050.199486601949, "count": 63540, "is_parallel": true, "self": 1050.199486601949 }, "steps_from_proto": { "total": 96.28404101600677, "count": 63540, "is_parallel": true, "self": 19.457452775945058, "children": { "_process_rank_one_or_two_observation": { "total": 76.82658824006171, "count": 508320, "is_parallel": true, "self": 76.82658824006171 } } } } } } } } } } }, "trainer_advance": { "total": 680.6529423749757, "count": 63541, "self": 2.4811862679077876, "children": { "process_trajectory": { "total": 130.59800858806466, "count": 63541, "self": 130.39093398206478, "children": { "RLTrainer._checkpoint": { "total": 0.20707460599987826, "count": 2, "self": 0.20707460599987826 } } }, "_update_policy": { "total": 547.5737475190033, "count": 453, "self": 308.575998019018, "children": { "TorchPPOOptimizer.update": { "total": 238.99774949998528, "count": 22818, "self": 238.99774949998528 } } } } } } }, "trainer_threads": { "total": 1.0969997674692422e-06, "count": 1, "self": 1.0969997674692422e-06 }, "TrainerController._save_models": { "total": 0.08260945499978334, "count": 1, "self": 0.0014763069998480205, "children": { "RLTrainer._checkpoint": { "total": 0.08113314799993532, "count": 1, "self": 0.08113314799993532 } } } } } } }