{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4138394892215729, "min": 0.4138394892215729, "max": 1.412109613418579, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12315.86328125, "min": 12315.86328125, "max": 42837.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29952.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.518382728099823, "min": -0.10136139392852783, "max": 0.5985098481178284, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.220703125, "min": -24.428096771240234, "max": 166.4949188232422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0035349696408957243, "min": -0.03492625430226326, "max": 0.2597792148590088, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0039314031600952, "min": -9.569793701171875, "max": 61.56767654418945, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06874363010727048, "min": 0.0641599292122108, "max": 0.07278203102485556, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9624108215017867, "min": 0.48823911470699594, "max": 1.084089665110999, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018067766540861202, "min": 0.00010226306763173388, "max": 0.018067766540861202, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25294873157205683, "min": 0.0012271568115808065, "max": 0.25294873157205683, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.424926096485714e-06, "min": 7.424926096485714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010394896535079999, "min": 0.00010394896535079999, "max": 0.003225738724753799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247494285714286, "min": 0.10247494285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346492, "min": 1.3886848, "max": 2.4427199000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002572467914285715, "min": 0.0002572467914285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036014550800000005, "min": 0.0036014550800000005, "max": 0.10753709538000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008488585241138935, "min": 0.008445687592029572, "max": 0.33495375514030457, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11884018778800964, "min": 0.118239626288414, "max": 2.3446762561798096, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.68817204301075, "min": 319.7752808988764, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32986.0, "min": 15984.0, "max": 33325.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6022881565875904, "min": -1.0000000521540642, "max": 1.6352718988161408, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.0127985626459, "min": -31.99760167300701, "max": 149.0127985626459, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6022881565875904, "min": -1.0000000521540642, "max": 1.6352718988161408, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.0127985626459, "min": -31.99760167300701, "max": 149.0127985626459, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03086536496947144, "min": 0.029677426450433905, "max": 6.666799647733569, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.870478942160844, "min": 2.403086661011912, "max": 106.6687943637371, "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": "1688279363", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/sid/anaconda3/envs/ml_env_39/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": "1688280386" }, "total": 1023.2850281540013, "count": 1, "self": 0.2179877970047528, "children": { "run_training.setup": { "total": 0.009620862998417579, "count": 1, "self": 0.009620862998417579 }, "TrainerController.start_learning": { "total": 1023.0574194939982, "count": 1, "self": 1.0052307417427073, "children": { "TrainerController._reset_env": { "total": 3.13729912800045, "count": 1, "self": 3.13729912800045 }, "TrainerController.advance": { "total": 1018.8513116382528, "count": 63803, "self": 0.9343267611548072, "children": { "env_step": { "total": 659.7895847937834, "count": 63803, "self": 577.93568506265, "children": { "SubprocessEnvManager._take_step": { "total": 81.21588144198904, "count": 63803, "self": 2.525574296625564, "children": { "TorchPolicy.evaluate": { "total": 78.69030714536348, "count": 62559, "self": 78.69030714536348 } } }, "workers": { "total": 0.6380182891443837, "count": 63803, "self": 0.0, "children": { "worker_root": { "total": 1021.759402175885, "count": 63803, "is_parallel": true, "self": 506.7127629476381, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00115087899757782, "count": 1, "is_parallel": true, "self": 0.00035785901127383113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007930199863039888, "count": 8, "is_parallel": true, "self": 0.0007930199863039888 } } }, "UnityEnvironment.step": { "total": 0.020688451993919443, "count": 1, "is_parallel": true, "self": 0.00019030199473490939, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021980699966661632, "count": 1, "is_parallel": true, "self": 0.00021980699966661632 }, "communicator.exchange": { "total": 0.019658046003314666, "count": 1, "is_parallel": true, "self": 0.019658046003314666 }, "steps_from_proto": { "total": 0.0006202969962032512, "count": 1, "is_parallel": true, "self": 0.00015613297728123143, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046416401892201975, "count": 8, "is_parallel": true, "self": 0.00046416401892201975 } } } } } } }, "UnityEnvironment.step": { "total": 515.0466392282469, "count": 63802, "is_parallel": true, "self": 17.689432605126058, "children": { "UnityEnvironment._generate_step_input": { "total": 9.513983640921651, "count": 63802, "is_parallel": true, "self": 9.513983640921651 }, "communicator.exchange": { "total": 441.5119834977668, "count": 63802, "is_parallel": true, "self": 441.5119834977668 }, "steps_from_proto": { "total": 46.331239484432444, "count": 63802, "is_parallel": true, "self": 9.623717039525218, "children": { "_process_rank_one_or_two_observation": { "total": 36.70752244490723, "count": 510416, "is_parallel": true, "self": 36.70752244490723 } } } } } } } } } } }, "trainer_advance": { "total": 358.12740008331457, "count": 63803, "self": 1.6656784963270184, "children": { "process_trajectory": { "total": 61.740722259019094, "count": 63803, "self": 61.61267711601977, "children": { "RLTrainer._checkpoint": { "total": 0.12804514299932634, "count": 2, "self": 0.12804514299932634 } } }, "_update_policy": { "total": 294.72099932796846, "count": 447, "self": 178.98836302058044, "children": { "TorchPPOOptimizer.update": { "total": 115.73263630738802, "count": 22848, "self": 115.73263630738802 } } } } } } }, "trainer_threads": { "total": 5.500041879713535e-07, "count": 1, "self": 5.500041879713535e-07 }, "TrainerController._save_models": { "total": 0.06357743599801324, "count": 1, "self": 0.0008700179969309829, "children": { "RLTrainer._checkpoint": { "total": 0.06270741800108226, "count": 1, "self": 0.06270741800108226 } } } } } } }