{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4316999018192291, "min": 0.421989381313324, "max": 1.3195972442626953, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12909.5537109375, "min": 12516.802734375, "max": 40031.30078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.29830682277679443, "min": -0.11266937851905823, "max": 0.3635011613368988, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 76.66485595703125, "min": -27.1533203125, "max": 97.0548095703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.18534629046916962, "min": -0.18534629046916962, "max": 0.4462178647518158, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -47.633995056152344, "min": -47.633995056152344, "max": 105.75363159179688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06584491073833003, "min": 0.06406263451531619, "max": 0.07292677738353204, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9218287503366204, "min": 0.5104874416847243, "max": 1.0474829023199468, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018234242230391825, "min": 0.0008391599448662501, "max": 0.018234242230391825, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25527939122548554, "min": 0.010909079283261252, "max": 0.25527939122548554, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.599311752642856e-06, "min": 7.599311752642856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010639036453699998, "min": 0.00010639036453699998, "max": 0.0033760807746397994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253307142857145, "min": 0.10253307142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354630000000002, "min": 1.3886848, "max": 2.4849942, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026305383571428566, "min": 0.00026305383571428566, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036827536999999994, "min": 0.0036827536999999994, "max": 0.11255348398, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009598984383046627, "min": 0.009586527943611145, "max": 0.583357036113739, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13438577950000763, "min": 0.13421139121055603, "max": 4.083499431610107, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 530.5593220338983, "min": 499.31666666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31303.0, "min": 15984.0, "max": 33622.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0625084417603783, "min": -1.0000000521540642, "max": 1.2730571141555196, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 62.687998063862324, "min": -29.92380166053772, "max": 80.20259819179773, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0625084417603783, "min": -1.0000000521540642, "max": 1.2730571141555196, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 62.687998063862324, "min": -29.92380166053772, "max": 80.20259819179773, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05305729107931256, "min": 0.0507644219414315, "max": 12.996365256607533, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.130380173679441, "min": 2.9443364726030268, "max": 207.94184410572052, "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": "1749106411", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/donglinbai/miniconda3/envs/mlagents/bin/mlagents-learn ./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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749107766" }, "total": 1354.6505958624184, "count": 1, "self": 0.3209068179130554, "children": { "run_training.setup": { "total": 0.02000090479850769, "count": 1, "self": 0.02000090479850769 }, "TrainerController.start_learning": { "total": 1354.3096881397069, "count": 1, "self": 0.8716510199010372, "children": { "TrainerController._reset_env": { "total": 2.3546367213129997, "count": 1, "self": 2.3546367213129997 }, "TrainerController.advance": { "total": 1350.9990602955222, "count": 63442, "self": 0.8318075723946095, "children": { "env_step": { "total": 870.2264582328498, "count": 63442, "self": 768.0745485462248, "children": { "SubprocessEnvManager._take_step": { "total": 101.62604968994856, "count": 63442, "self": 3.133396804332733, "children": { "TorchPolicy.evaluate": { "total": 98.49265288561583, "count": 62570, "self": 98.49265288561583 } } }, "workers": { "total": 0.525859996676445, "count": 63442, "self": 0.0, "children": { "worker_root": { "total": 1352.8851497396827, "count": 63442, "is_parallel": true, "self": 655.8277734667063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001678410917520523, "count": 1, "is_parallel": true, "self": 0.0005264505743980408, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011519603431224823, "count": 8, "is_parallel": true, "self": 0.0011519603431224823 } } }, "UnityEnvironment.step": { "total": 0.027298782020807266, "count": 1, "is_parallel": true, "self": 0.00028593093156814575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002638772130012512, "count": 1, "is_parallel": true, "self": 0.0002638772130012512 }, "communicator.exchange": { "total": 0.025890380144119263, "count": 1, "is_parallel": true, "self": 0.025890380144119263 }, "steps_from_proto": { "total": 0.0008585937321186066, "count": 1, "is_parallel": true, "self": 0.00020154565572738647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006570480763912201, "count": 8, "is_parallel": true, "self": 0.0006570480763912201 } } } } } } }, "UnityEnvironment.step": { "total": 697.0573762729764, "count": 63441, "is_parallel": true, "self": 16.39208796620369, "children": { "UnityEnvironment._generate_step_input": { "total": 11.20337351411581, "count": 63441, "is_parallel": true, "self": 11.20337351411581 }, "communicator.exchange": { "total": 623.5176570154727, "count": 63441, "is_parallel": true, "self": 623.5176570154727 }, "steps_from_proto": { "total": 45.94425777718425, "count": 63441, "is_parallel": true, "self": 9.422534488141537, "children": { "_process_rank_one_or_two_observation": { "total": 36.52172328904271, "count": 507528, "is_parallel": true, "self": 36.52172328904271 } } } } } } } } } } }, "trainer_advance": { "total": 479.94079449027777, "count": 63442, "self": 1.5908168330788612, "children": { "process_trajectory": { "total": 93.24763160943985, "count": 63442, "self": 93.06171968951821, "children": { "RLTrainer._checkpoint": { "total": 0.18591191992163658, "count": 2, "self": 0.18591191992163658 } } }, "_update_policy": { "total": 385.10234604775906, "count": 449, "self": 210.8282284513116, "children": { "TorchPPOOptimizer.update": { "total": 174.27411759644747, "count": 22836, "self": 174.27411759644747 } } } } } } }, "trainer_threads": { "total": 7.972121238708496e-07, "count": 1, "self": 7.972121238708496e-07 }, "TrainerController._save_models": { "total": 0.08433930575847626, "count": 1, "self": 0.001476578414440155, "children": { "RLTrainer._checkpoint": { "total": 0.0828627273440361, "count": 1, "self": 0.0828627273440361 } } } } } } }