{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30673474073410034, "min": 0.2941080331802368, "max": 1.43389093875885, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9241.3046875, "min": 8776.18359375, "max": 43498.515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6415443420410156, "min": -0.10133643448352814, "max": 0.6656767129898071, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.0478515625, "min": -24.016735076904297, "max": 190.383544921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01243357639759779, "min": -0.020878516137599945, "max": 0.32849717140197754, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.6057372093200684, "min": -5.574563980102539, "max": 77.85382843017578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07186666038959368, "min": 0.06389208699831561, "max": 0.07214547131960797, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0061332454543115, "min": 0.48045592711875135, "max": 1.0821820697941196, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015564470291277914, "min": 0.0011841943604725678, "max": 0.017090847395837865, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2179025840778908, "min": 0.014126499046763049, "max": 0.24508172458930252, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.359590403978569e-06, "min": 7.359590403978569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010303426565569997, "min": 0.00010303426565569997, "max": 0.0035080289306571, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024531642857143, "min": 0.1024531642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343443000000002, "min": 1.3886848, "max": 2.5693429000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002550711121428571, "min": 0.0002550711121428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00357099557, "min": 0.00357099557, "max": 0.11695735571, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011340707540512085, "min": 0.011340707540512085, "max": 0.4810614585876465, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1587699055671692, "min": 0.1587699055671692, "max": 3.3674302101135254, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 286.747572815534, "min": 283.7641509433962, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29535.0, "min": 15984.0, "max": 32647.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6938291083551147, "min": -1.0000000521540642, "max": 1.6938291083551147, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.46439816057682, "min": -29.822001673281193, "max": 177.49979834258556, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6938291083551147, "min": -1.0000000521540642, "max": 1.6938291083551147, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.46439816057682, "min": -29.822001673281193, "max": 177.49979834258556, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033742186601513326, "min": 0.033742186601513326, "max": 9.869948073290288, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4754452199558727, "min": 3.4754452199558727, "max": 157.91916917264462, "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": "1696153022", "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": "1696155367" }, "total": 2344.655226598, "count": 1, "self": 0.5321692919997076, "children": { "run_training.setup": { "total": 0.03946158700000524, "count": 1, "self": 0.03946158700000524 }, "TrainerController.start_learning": { "total": 2344.083595719, "count": 1, "self": 1.3989849359122672, "children": { "TrainerController._reset_env": { "total": 4.110515498000041, "count": 1, "self": 4.110515498000041 }, "TrainerController.advance": { "total": 2338.480293897088, "count": 64206, "self": 1.3773935240183164, "children": { "env_step": { "total": 1666.046727147993, "count": 64206, "self": 1557.5364348571009, "children": { "SubprocessEnvManager._take_step": { "total": 107.70406788695618, "count": 64206, "self": 4.776943906951146, "children": { "TorchPolicy.evaluate": { "total": 102.92712398000504, "count": 62557, "self": 102.92712398000504 } } }, "workers": { "total": 0.8062244039358575, "count": 64206, "self": 0.0, "children": { "worker_root": { "total": 2338.714743832941, "count": 64206, "is_parallel": true, "self": 895.0975958149634, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001961150999932215, "count": 1, "is_parallel": true, "self": 0.0005773919997409394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013837590001912758, "count": 8, "is_parallel": true, "self": 0.0013837590001912758 } } }, "UnityEnvironment.step": { "total": 0.04788464899979772, "count": 1, "is_parallel": true, "self": 0.0005656909995650494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046612699998149765, "count": 1, "is_parallel": true, "self": 0.00046612699998149765 }, "communicator.exchange": { "total": 0.04408341700013807, "count": 1, "is_parallel": true, "self": 0.04408341700013807 }, "steps_from_proto": { "total": 0.002769414000113102, "count": 1, "is_parallel": true, "self": 0.0003856750004160858, "children": { "_process_rank_one_or_two_observation": { "total": 0.002383738999697016, "count": 8, "is_parallel": true, "self": 0.002383738999697016 } } } } } } }, "UnityEnvironment.step": { "total": 1443.6171480179778, "count": 64205, "is_parallel": true, "self": 34.695298113032095, "children": { "UnityEnvironment._generate_step_input": { "total": 23.187240528015536, "count": 64205, "is_parallel": true, "self": 23.187240528015536 }, "communicator.exchange": { "total": 1277.7411202869932, "count": 64205, "is_parallel": true, "self": 1277.7411202869932 }, "steps_from_proto": { "total": 107.99348908993693, "count": 64205, "is_parallel": true, "self": 21.23639834591836, "children": { "_process_rank_one_or_two_observation": { "total": 86.75709074401857, "count": 513640, "is_parallel": true, "self": 86.75709074401857 } } } } } } } } } } }, "trainer_advance": { "total": 671.0561732250767, "count": 64206, "self": 2.5605394950105165, "children": { "process_trajectory": { "total": 111.66055921407224, "count": 64206, "self": 111.45526581107197, "children": { "RLTrainer._checkpoint": { "total": 0.20529340300026888, "count": 2, "self": 0.20529340300026888 } } }, "_update_policy": { "total": 556.8350745159939, "count": 450, "self": 364.13900999502334, "children": { "TorchPPOOptimizer.update": { "total": 192.6960645209706, "count": 22821, "self": 192.6960645209706 } } } } } } }, "trainer_threads": { "total": 1.0130002010555472e-06, "count": 1, "self": 1.0130002010555472e-06 }, "TrainerController._save_models": { "total": 0.09380037499977334, "count": 1, "self": 0.0014901999998073734, "children": { "RLTrainer._checkpoint": { "total": 0.09231017499996597, "count": 1, "self": 0.09231017499996597 } } } } } } }