{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2489519715309143, "min": 0.2489519715309143, "max": 1.4669841527938843, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7428.72705078125, "min": 7428.72705078125, "max": 44502.4296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5124466419219971, "min": -0.2877480089664459, "max": 0.5487314462661743, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.4850616455078, "min": -68.19628143310547, "max": 152.02597045898438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030395343899726868, "min": -0.0003370176418684423, "max": 0.2623296082019806, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.510696411132812, "min": -0.09133177995681763, "max": 63.221435546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06603833254415631, "min": 0.06584203734411748, "max": 0.07328428389656673, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9245366556181883, "min": 0.5106062959612351, "max": 1.0259799745519342, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018080309787321662, "min": 0.002761668531145581, "max": 0.018080309787321662, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25312433702250325, "min": 0.03146308408188282, "max": 0.25312433702250325, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.484090362478575e-06, "min": 7.484090362478575e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010477726507470005, "min": 0.00010477726507470005, "max": 0.0036364810878396995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249466428571428, "min": 0.10249466428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349253, "min": 1.3886848, "max": 2.6121602999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025921696214285724, "min": 0.00025921696214285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036290374700000015, "min": 0.0036290374700000015, "max": 0.12123481397000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011008987203240395, "min": 0.010712387040257454, "max": 0.4144280254840851, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15412582457065582, "min": 0.14997342228889465, "max": 2.900996208190918, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.86021505376345, "min": 316.86021505376345, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29468.0, "min": 15984.0, "max": 33799.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5540688009031358, "min": -1.0000000521540642, "max": 1.6205823986412404, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.52839848399162, "min": -25.829201854765415, "max": 147.47299827635288, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5540688009031358, "min": -1.0000000521540642, "max": 1.6205823986412404, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.52839848399162, "min": -25.829201854765415, "max": 147.47299827635288, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035581812776389825, "min": 0.035581812776389825, "max": 7.935018887743354, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3091085882042535, "min": 3.3091085882042535, "max": 126.96030220389366, "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": "1788881146", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788883790" }, "total": 2644.080674406, "count": 1, "self": 0.5315609929998573, "children": { "run_training.setup": { "total": 0.026479308000034507, "count": 1, "self": 0.026479308000034507 }, "TrainerController.start_learning": { "total": 2643.522634105, "count": 1, "self": 1.5234119410670246, "children": { "TrainerController._reset_env": { "total": 2.9418081320000056, "count": 1, "self": 2.9418081320000056 }, "TrainerController.advance": { "total": 2638.977447081933, "count": 63987, "self": 1.6090976569812483, "children": { "env_step": { "total": 1976.5475753939372, "count": 63987, "self": 1813.8907692720795, "children": { "SubprocessEnvManager._take_step": { "total": 161.788031382996, "count": 63987, "self": 5.035329731181719, "children": { "TorchPolicy.evaluate": { "total": 156.75270165181428, "count": 62567, "self": 156.75270165181428 } } }, "workers": { "total": 0.8687747388617026, "count": 63987, "self": 0.0, "children": { "worker_root": { "total": 2637.751978882042, "count": 63987, "is_parallel": true, "self": 951.3819037270282, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028143019999333774, "count": 1, "is_parallel": true, "self": 0.0007679330001337803, "children": { "_process_rank_one_or_two_observation": { "total": 0.002046368999799597, "count": 8, "is_parallel": true, "self": 0.002046368999799597 } } }, "UnityEnvironment.step": { "total": 0.11119617399981507, "count": 1, "is_parallel": true, "self": 0.001330385999608552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004999580000912829, "count": 1, "is_parallel": true, "self": 0.0004999580000912829 }, "communicator.exchange": { "total": 0.10222901499992076, "count": 1, "is_parallel": true, "self": 0.10222901499992076 }, "steps_from_proto": { "total": 0.007136815000194474, "count": 1, "is_parallel": true, "self": 0.0024100410005303274, "children": { "_process_rank_one_or_two_observation": { "total": 0.004726773999664147, "count": 8, "is_parallel": true, "self": 0.004726773999664147 } } } } } } }, "UnityEnvironment.step": { "total": 1686.3700751550136, "count": 63986, "is_parallel": true, "self": 36.41499389389037, "children": { "UnityEnvironment._generate_step_input": { "total": 25.9553956051177, "count": 63986, "is_parallel": true, "self": 25.9553956051177 }, "communicator.exchange": { "total": 1504.1004446799493, "count": 63986, "is_parallel": true, "self": 1504.1004446799493 }, "steps_from_proto": { "total": 119.89924097605626, "count": 63986, "is_parallel": true, "self": 24.576497510021454, "children": { "_process_rank_one_or_two_observation": { "total": 95.32274346603481, "count": 511888, "is_parallel": true, "self": 95.32274346603481 } } } } } } } } } } }, "trainer_advance": { "total": 660.8207740310145, "count": 63987, "self": 2.8329302130100587, "children": { "process_trajectory": { "total": 120.03945520699244, "count": 63987, "self": 119.79356494999274, "children": { "RLTrainer._checkpoint": { "total": 0.2458902569997008, "count": 2, "self": 0.2458902569997008 } } }, "_update_policy": { "total": 537.948388611012, "count": 460, "self": 288.22455214594856, "children": { "TorchPPOOptimizer.update": { "total": 249.7238364650634, "count": 22779, "self": 249.7238364650634 } } } } } } }, "trainer_threads": { "total": 1.0470002962392755e-06, "count": 1, "self": 1.0470002962392755e-06 }, "TrainerController._save_models": { "total": 0.07996590299990203, "count": 1, "self": 0.0011050289995182538, "children": { "RLTrainer._checkpoint": { "total": 0.07886087400038377, "count": 1, "self": 0.07886087400038377 } } } } } } }