{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42157360911369324, "min": 0.42157360911369324, "max": 1.4251736402511597, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12728.150390625, "min": 12728.150390625, "max": 43234.06640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5318320989608765, "min": -0.11421607434749603, "max": 0.5980802774429321, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.19017028808594, "min": -27.526073455810547, "max": 169.85479736328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015953175723552704, "min": 0.0016481210477650166, "max": 0.48571404814720154, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.355216979980469, "min": 0.42191898822784424, "max": 117.05708312988281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04377963589961707, "min": 0.04189062842245524, "max": 0.05248152685998759, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.612914902594639, "min": 0.3475619731588744, "max": 0.750370929716155, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015278123019795335, "min": 0.0011519146382547667, "max": 0.015278123019795335, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21389372227713468, "min": 0.014974890297311968, "max": 0.21389372227713468, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.307968992614287e-06, "min": 7.307968992614287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010231156589660002, "min": 0.00010231156589660002, "max": 0.0036354433881855995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243595714285715, "min": 0.10243595714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341034000000001, "min": 1.3886848, "max": 2.6118144, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025335211857142865, "min": 0.00025335211857142865, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035469296600000007, "min": 0.0035469296600000007, "max": 0.12120025856000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01368300337344408, "min": 0.01368300337344408, "max": 0.6789034605026245, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19156204164028168, "min": 0.19156204164028168, "max": 4.752324104309082, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 362.7590361445783, "min": 328.38461538461536, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30109.0, "min": 15984.0, "max": 33128.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5663166457698459, "min": -1.0000000521540642, "max": 1.6492844233910242, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.57059824466705, "min": -27.697401605546474, "max": 148.43559810519218, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5663166457698459, "min": -1.0000000521540642, "max": 1.6492844233910242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.57059824466705, "min": -27.697401605546474, "max": 148.43559810519218, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05057172488748273, "min": 0.05057172488748273, "max": 10.335547968745232, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.24802489054855, "min": 4.24802489054855, "max": 165.3687674999237, "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": "1702032045", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/my_PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702035528" }, "total": 3482.4810775789992, "count": 1, "self": 0.6810215739988053, "children": { "run_training.setup": { "total": 0.0694756269986101, "count": 1, "self": 0.0694756269986101 }, "TrainerController.start_learning": { "total": 3481.730580378002, "count": 1, "self": 2.3261368683906767, "children": { "TrainerController._reset_env": { "total": 2.679652064000038, "count": 1, "self": 2.679652064000038 }, "TrainerController.advance": { "total": 3476.604878151613, "count": 63782, "self": 2.7929845573944476, "children": { "env_step": { "total": 2295.050792565813, "count": 63782, "self": 2100.9506547301535, "children": { "SubprocessEnvManager._take_step": { "total": 192.62745538104173, "count": 63782, "self": 7.354213691967743, "children": { "TorchPolicy.evaluate": { "total": 185.27324168907398, "count": 62548, "self": 185.27324168907398 } } }, "workers": { "total": 1.472682454617825, "count": 63782, "self": 0.0, "children": { "worker_root": { "total": 3475.43099021102, "count": 63782, "is_parallel": true, "self": 1549.6535590301391, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002890540999942459, "count": 1, "is_parallel": true, "self": 0.000980262999291881, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019102780006505782, "count": 8, "is_parallel": true, "self": 0.0019102780006505782 } } }, "UnityEnvironment.step": { "total": 0.06459023699972022, "count": 1, "is_parallel": true, "self": 0.0006779619998269482, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005244799995125504, "count": 1, "is_parallel": true, "self": 0.0005244799995125504 }, "communicator.exchange": { "total": 0.06126786599998013, "count": 1, "is_parallel": true, "self": 0.06126786599998013 }, "steps_from_proto": { "total": 0.002119929000400589, "count": 1, "is_parallel": true, "self": 0.0004555239975161385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016644050028844504, "count": 8, "is_parallel": true, "self": 0.0016644050028844504 } } } } } } }, "UnityEnvironment.step": { "total": 1925.7774311808807, "count": 63781, "is_parallel": true, "self": 46.49494442758623, "children": { "UnityEnvironment._generate_step_input": { "total": 27.94560197733699, "count": 63781, "is_parallel": true, "self": 27.94560197733699 }, "communicator.exchange": { "total": 1720.4833714440938, "count": 63781, "is_parallel": true, "self": 1720.4833714440938 }, "steps_from_proto": { "total": 130.85351333186372, "count": 63781, "is_parallel": true, "self": 28.119476643838425, "children": { "_process_rank_one_or_two_observation": { "total": 102.7340366880253, "count": 510248, "is_parallel": true, "self": 102.7340366880253 } } } } } } } } } } }, "trainer_advance": { "total": 1178.7611010284054, "count": 63782, "self": 4.697270052234671, "children": { "process_trajectory": { "total": 185.96515311317125, "count": 63782, "self": 185.64768895417183, "children": { "RLTrainer._checkpoint": { "total": 0.31746415899942804, "count": 2, "self": 0.31746415899942804 } } }, "_update_policy": { "total": 988.0986778629995, "count": 458, "self": 332.76158416100225, "children": { "TorchPPOOptimizer.update": { "total": 655.3370937019972, "count": 11298, "self": 655.3370937019972 } } } } } } }, "trainer_threads": { "total": 1.4709985407534987e-06, "count": 1, "self": 1.4709985407534987e-06 }, "TrainerController._save_models": { "total": 0.11991182299971115, "count": 1, "self": 0.0029768940003123134, "children": { "RLTrainer._checkpoint": { "total": 0.11693492899939884, "count": 1, "self": 0.11693492899939884 } } } } } } }