{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5668575763702393, "min": 0.5668575763702393, "max": 1.5003933906555176, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16688.287109375, "min": 16688.287109375, "max": 45515.93359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44275522232055664, "min": -0.11162517219781876, "max": 0.4912421405315399, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 120.4294204711914, "min": -26.45516586303711, "max": 131.65289306640625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003676940919831395, "min": -0.03192926570773125, "max": 0.45653781294822693, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.000127911567688, "min": -8.429326057434082, "max": 109.56907653808594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06965881134480394, "min": 0.06576677313395997, "max": 0.07470372419020396, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9752233588272551, "min": 0.5229260693314277, "max": 1.060169493111864, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014178328122874345, "min": 0.0005209369161291764, "max": 0.015515092264866413, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19849659372024084, "min": 0.006772179909679293, "max": 0.2243169403111952, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4621689412142885e-06, "min": 7.4621689412142885e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010447036517700004, "min": 0.00010447036517700004, "max": 0.0035075849308050995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248735714285714, "min": 0.10248735714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.434823, "min": 1.3886848, "max": 2.5691949000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584869785714287, "min": 0.0002584869785714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036188177000000014, "min": 0.0036188177000000014, "max": 0.11694257050999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009351393207907677, "min": 0.009351393207907677, "max": 0.7007805109024048, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13091950118541718, "min": 0.13091950118541718, "max": 4.905463695526123, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 415.38028169014086, "min": 383.9875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29492.0, "min": 15984.0, "max": 32599.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.557725696691445, "min": -1.0000000521540642, "max": 1.557725696691445, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 109.04079876840115, "min": -30.610801726579666, "max": 121.27919799089432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.557725696691445, "min": -1.0000000521540642, "max": 1.557725696691445, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 109.04079876840115, "min": -30.610801726579666, "max": 121.27919799089432, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04123045702726813, "min": 0.04123045702726813, "max": 14.711938962340355, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.886131991908769, "min": 2.886131991908769, "max": 235.39102339744568, "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": "1710418086", "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/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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710420311" }, "total": 2224.6924702260003, "count": 1, "self": 0.47674695499972586, "children": { "run_training.setup": { "total": 0.07659858700003497, "count": 1, "self": 0.07659858700003497 }, "TrainerController.start_learning": { "total": 2224.1391246840003, "count": 1, "self": 1.3604390320510902, "children": { "TrainerController._reset_env": { "total": 2.7587029730000268, "count": 1, "self": 2.7587029730000268 }, "TrainerController.advance": { "total": 2219.935771073949, "count": 63597, "self": 1.5034956469721692, "children": { "env_step": { "total": 1594.0059344129836, "count": 63597, "self": 1461.3845302169632, "children": { "SubprocessEnvManager._take_step": { "total": 131.73009593199276, "count": 63597, "self": 4.613137636998545, "children": { "TorchPolicy.evaluate": { "total": 127.11695829499422, "count": 62551, "self": 127.11695829499422 } } }, "workers": { "total": 0.8913082640276571, "count": 63597, "self": 0.0, "children": { "worker_root": { "total": 2218.943922788983, "count": 63597, "is_parallel": true, "self": 878.4800028229884, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002891296999905535, "count": 1, "is_parallel": true, "self": 0.0007435740003529645, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021477229995525704, "count": 8, "is_parallel": true, "self": 0.0021477229995525704 } } }, "UnityEnvironment.step": { "total": 0.04909837300010622, "count": 1, "is_parallel": true, "self": 0.0006800970004405826, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004378369999358256, "count": 1, "is_parallel": true, "self": 0.0004378369999358256 }, "communicator.exchange": { "total": 0.04618597599983332, "count": 1, "is_parallel": true, "self": 0.04618597599983332 }, "steps_from_proto": { "total": 0.0017944629998964956, "count": 1, "is_parallel": true, "self": 0.00036050400012754835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014339589997689473, "count": 8, "is_parallel": true, "self": 0.0014339589997689473 } } } } } } }, "UnityEnvironment.step": { "total": 1340.4639199659946, "count": 63596, "is_parallel": true, "self": 35.15677330601034, "children": { "UnityEnvironment._generate_step_input": { "total": 24.057377680922855, "count": 63596, "is_parallel": true, "self": 24.057377680922855 }, "communicator.exchange": { "total": 1180.774304113042, "count": 63596, "is_parallel": true, "self": 1180.774304113042 }, "steps_from_proto": { "total": 100.47546486601937, "count": 63596, "is_parallel": true, "self": 20.378501794964905, "children": { "_process_rank_one_or_two_observation": { "total": 80.09696307105446, "count": 508768, "is_parallel": true, "self": 80.09696307105446 } } } } } } } } } } }, "trainer_advance": { "total": 624.4263410139936, "count": 63597, "self": 2.6130925899315116, "children": { "process_trajectory": { "total": 124.55355941506059, "count": 63597, "self": 124.35728437206035, "children": { "RLTrainer._checkpoint": { "total": 0.19627504300024157, "count": 2, "self": 0.19627504300024157 } } }, "_update_policy": { "total": 497.2596890090015, "count": 449, "self": 292.0209135789901, "children": { "TorchPPOOptimizer.update": { "total": 205.2387754300114, "count": 22764, "self": 205.2387754300114 } } } } } } }, "trainer_threads": { "total": 9.680002222012263e-07, "count": 1, "self": 9.680002222012263e-07 }, "TrainerController._save_models": { "total": 0.08421063700006926, "count": 1, "self": 0.0013330120000318857, "children": { "RLTrainer._checkpoint": { "total": 0.08287762500003737, "count": 1, "self": 0.08287762500003737 } } } } } } }