{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5112035870552063, "min": 0.5063225626945496, "max": 1.516282558441162, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15409.720703125, "min": 14938.541015625, "max": 45997.94921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4832257628440857, "min": -0.11065292358398438, "max": 0.5055014491081238, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 130.9541778564453, "min": -26.224742889404297, "max": 139.51840209960938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.7989873290061951, "min": -0.7989873290061951, "max": 0.29903644323349, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -216.52557373046875, "min": -216.52557373046875, "max": 70.87163543701172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07238166209659865, "min": 0.06395778312123315, "max": 0.0725229596887899, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.013343269352381, "min": 0.4829356626071566, "max": 1.0720752131424423, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.08947690260216347, "min": 0.0003245817913297684, "max": 0.08947690260216347, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.2526766364302886, "min": 0.002600098041849096, "max": 1.2526766364302886, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.423126097085709e-06, "min": 7.423126097085709e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010392376535919993, "min": 0.00010392376535919993, "max": 0.0031174447608517987, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247434285714285, "min": 0.10247434285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346408, "min": 1.3691136000000002, "max": 2.360223, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002571868514285713, "min": 0.0002571868514285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036006159199999986, "min": 0.0036006159199999986, "max": 0.10393090518, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010999622754752636, "min": 0.010999622754752636, "max": 0.40126508474349976, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15399472415447235, "min": 0.15399472415447235, "max": 2.8088555335998535, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 352.7283950617284, "min": 352.7283950617284, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28571.0, "min": 15984.0, "max": 32783.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.548481456199546, "min": -1.0000000521540642, "max": 1.548481456199546, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.42699795216322, "min": -32.000001668930054, "max": 125.42699795216322, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.548481456199546, "min": -1.0000000521540642, "max": 1.548481456199546, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.42699795216322, "min": -32.000001668930054, "max": 125.42699795216322, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03995880967560857, "min": 0.03995880967560857, "max": 8.20104026608169, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.236663583724294, "min": 3.236663583724294, "max": 131.21664425730705, "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": "1734891084", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734893327" }, "total": 2243.255056635, "count": 1, "self": 0.48886308100009046, "children": { "run_training.setup": { "total": 0.060091784999997344, "count": 1, "self": 0.060091784999997344 }, "TrainerController.start_learning": { "total": 2242.706101769, "count": 1, "self": 1.3866447920290739, "children": { "TrainerController._reset_env": { "total": 5.009039933999986, "count": 1, "self": 5.009039933999986 }, "TrainerController.advance": { "total": 2236.2261769089705, "count": 63545, "self": 1.4594259969589984, "children": { "env_step": { "total": 1542.2076357700037, "count": 63545, "self": 1388.9387970970279, "children": { "SubprocessEnvManager._take_step": { "total": 152.42649109600444, "count": 63545, "self": 4.612683412975912, "children": { "TorchPolicy.evaluate": { "total": 147.81380768302853, "count": 62566, "self": 147.81380768302853 } } }, "workers": { "total": 0.8423475769714059, "count": 63545, "self": 0.0, "children": { "worker_root": { "total": 2237.618867277012, "count": 63545, "is_parallel": true, "self": 965.1846028860018, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019788810000136436, "count": 1, "is_parallel": true, "self": 0.0006080969999970876, "children": { "_process_rank_one_or_two_observation": { "total": 0.001370784000016556, "count": 8, "is_parallel": true, "self": 0.001370784000016556 } } }, "UnityEnvironment.step": { "total": 0.12371154699997078, "count": 1, "is_parallel": true, "self": 0.0006499189999544797, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043535200001088015, "count": 1, "is_parallel": true, "self": 0.00043535200001088015 }, "communicator.exchange": { "total": 0.1209452580000061, "count": 1, "is_parallel": true, "self": 0.1209452580000061 }, "steps_from_proto": { "total": 0.0016810179999993125, "count": 1, "is_parallel": true, "self": 0.0003540959999668303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013269220000324822, "count": 8, "is_parallel": true, "self": 0.0013269220000324822 } } } } } } }, "UnityEnvironment.step": { "total": 1272.4342643910104, "count": 63544, "is_parallel": true, "self": 32.923150801956126, "children": { "UnityEnvironment._generate_step_input": { "total": 23.086549801023693, "count": 63544, "is_parallel": true, "self": 23.086549801023693 }, "communicator.exchange": { "total": 1118.4931931200217, "count": 63544, "is_parallel": true, "self": 1118.4931931200217 }, "steps_from_proto": { "total": 97.93137066800892, "count": 63544, "is_parallel": true, "self": 19.846167619070116, "children": { "_process_rank_one_or_two_observation": { "total": 78.08520304893881, "count": 508352, "is_parallel": true, "self": 78.08520304893881 } } } } } } } } } } }, "trainer_advance": { "total": 692.559115142008, "count": 63545, "self": 2.5660661350558485, "children": { "process_trajectory": { "total": 134.12769244695102, "count": 63545, "self": 133.87937312995115, "children": { "RLTrainer._checkpoint": { "total": 0.24831931699986853, "count": 2, "self": 0.24831931699986853 } } }, "_update_policy": { "total": 555.865356560001, "count": 435, "self": 311.2102480449721, "children": { "TorchPPOOptimizer.update": { "total": 244.65510851502893, "count": 22854, "self": 244.65510851502893 } } } } } } }, "trainer_threads": { "total": 9.76000137598021e-07, "count": 1, "self": 9.76000137598021e-07 }, "TrainerController._save_models": { "total": 0.08423915799994575, "count": 1, "self": 0.0014583209999727842, "children": { "RLTrainer._checkpoint": { "total": 0.08278083699997296, "count": 1, "self": 0.08278083699997296 } } } } } } }