{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5663087368011475, "min": 0.5663087368011475, "max": 1.4094384908676147, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17097.994140625, "min": 17097.994140625, "max": 42756.7265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5567012429237366, "min": -0.09065807610750198, "max": 0.5567012429237366, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.09283447265625, "min": -21.667280197143555, "max": 153.09283447265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0598287470638752, "min": -0.02408597804605961, "max": 0.4589160680770874, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.452905654907227, "min": -6.62364387512207, "max": 108.76310729980469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06480808763428487, "min": 0.06480808763428487, "max": 0.07381701551474157, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9721213145142731, "min": 0.5153528509126981, "max": 1.070874873335318, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013426881680950629, "min": 0.00014813732874517142, "max": 0.016288843025318547, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20140322521425943, "min": 0.0020739226024323997, "max": 0.22804380235445965, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.487957504046672e-06, "min": 7.487957504046672e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011231936256070007, "min": 0.00011231936256070007, "max": 0.0036331429889524002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249595333333335, "min": 0.10249595333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374393000000002, "min": 1.3886848, "max": 2.6110476, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025934573800000016, "min": 0.00025934573800000016, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038901860700000027, "min": 0.0038901860700000027, "max": 0.12112365523999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008682744577527046, "min": 0.008682744577527046, "max": 0.40611937642097473, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13024117052555084, "min": 0.12238536030054092, "max": 2.8428356647491455, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 365.1927710843373, "min": 344.09302325581393, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30311.0, "min": 15984.0, "max": 33121.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5383758886930454, "min": -1.0000000521540642, "max": 1.59987207172915, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.68519876152277, "min": -31.993201687932014, "max": 137.5889981687069, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5383758886930454, "min": -1.0000000521540642, "max": 1.59987207172915, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.68519876152277, "min": -31.993201687932014, "max": 137.5889981687069, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03249630308113936, "min": 0.032242576374407035, "max": 8.243971281684935, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.697193155734567, "min": 2.697193155734567, "max": 131.90354050695896, "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": "1724051716", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724054085" }, "total": 2369.435690661, "count": 1, "self": 0.5268064800002321, "children": { "run_training.setup": { "total": 0.05440402899967012, "count": 1, "self": 0.05440402899967012 }, "TrainerController.start_learning": { "total": 2368.854480152, "count": 1, "self": 1.8050425470491973, "children": { "TrainerController._reset_env": { "total": 2.1544526079997013, "count": 1, "self": 2.1544526079997013 }, "TrainerController.advance": { "total": 2364.7932338179517, "count": 63732, "self": 1.893471556905297, "children": { "env_step": { "total": 1693.4196136890996, "count": 63732, "self": 1529.7205243622147, "children": { "SubprocessEnvManager._take_step": { "total": 162.5665858549046, "count": 63732, "self": 5.666840212965326, "children": { "TorchPolicy.evaluate": { "total": 156.89974564193926, "count": 62566, "self": 156.89974564193926 } } }, "workers": { "total": 1.1325034719802716, "count": 63732, "self": 0.0, "children": { "worker_root": { "total": 2362.6546621050597, "count": 63732, "is_parallel": true, "self": 979.7565744391163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00293819699982123, "count": 1, "is_parallel": true, "self": 0.0007431489993905416, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021950480004306883, "count": 8, "is_parallel": true, "self": 0.0021950480004306883 } } }, "UnityEnvironment.step": { "total": 0.04830731200036098, "count": 1, "is_parallel": true, "self": 0.0006289989996730583, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004888120001851348, "count": 1, "is_parallel": true, "self": 0.0004888120001851348 }, "communicator.exchange": { "total": 0.0453961570001411, "count": 1, "is_parallel": true, "self": 0.0453961570001411 }, "steps_from_proto": { "total": 0.0017933440003616852, "count": 1, "is_parallel": true, "self": 0.0003828690005320823, "children": { "_process_rank_one_or_two_observation": { "total": 0.001410474999829603, "count": 8, "is_parallel": true, "self": 0.001410474999829603 } } } } } } }, "UnityEnvironment.step": { "total": 1382.8980876659434, "count": 63731, "is_parallel": true, "self": 38.41560472984702, "children": { "UnityEnvironment._generate_step_input": { "total": 26.215053359072044, "count": 63731, "is_parallel": true, "self": 26.215053359072044 }, "communicator.exchange": { "total": 1205.871665029019, "count": 63731, "is_parallel": true, "self": 1205.871665029019 }, "steps_from_proto": { "total": 112.39576454800545, "count": 63731, "is_parallel": true, "self": 24.237985720020333, "children": { "_process_rank_one_or_two_observation": { "total": 88.15777882798511, "count": 509848, "is_parallel": true, "self": 88.15777882798511 } } } } } } } } } } }, "trainer_advance": { "total": 669.4801485719468, "count": 63732, "self": 3.4620545208990734, "children": { "process_trajectory": { "total": 140.27421462904113, "count": 63732, "self": 140.06404707804177, "children": { "RLTrainer._checkpoint": { "total": 0.21016755099935835, "count": 2, "self": 0.21016755099935835 } } }, "_update_policy": { "total": 525.7438794220066, "count": 452, "self": 310.31613117500274, "children": { "TorchPPOOptimizer.update": { "total": 215.42774824700382, "count": 22818, "self": 215.42774824700382 } } } } } } }, "trainer_threads": { "total": 1.3310000213095918e-06, "count": 1, "self": 1.3310000213095918e-06 }, "TrainerController._save_models": { "total": 0.1017498479995993, "count": 1, "self": 0.0018374889996266575, "children": { "RLTrainer._checkpoint": { "total": 0.09991235899997264, "count": 1, "self": 0.09991235899997264 } } } } } } }