{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5244330763816833, "min": 0.49391767382621765, "max": 1.376940131187439, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15867.248046875, "min": 14770.1142578125, "max": 41770.85546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989960.0, "min": 29952.0, "max": 989960.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5227617621421814, "min": -0.10746748000383377, "max": 0.5227617621421814, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 143.23672485351562, "min": -25.792194366455078, "max": 143.23672485351562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0062320902943611145, "min": -0.0672081783413887, "max": 0.3009660542011261, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7075927257537842, "min": -17.87737464904785, "max": 72.53282165527344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06777164137160636, "min": 0.06332479434415433, "max": 0.07315732904022469, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9488029792024891, "min": 0.49296982297787556, "max": 1.0895461224512581, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015019271830572122, "min": 0.0006469993214584948, "max": 0.01590657178859969, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2102698056280097, "min": 0.007116992536043443, "max": 0.22269200504039569, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.746825989185718e-06, "min": 7.746825989185718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010845556384860004, "min": 0.00010845556384860004, "max": 0.0035083067305644996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258224285714286, "min": 0.10258224285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361514, "min": 1.3886848, "max": 2.5694355, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026796606142857156, "min": 0.00026796606142857156, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037515248600000018, "min": 0.0037515248600000018, "max": 0.11696660644999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008687565103173256, "min": 0.008687565103173256, "max": 0.49866923689842224, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12162591516971588, "min": 0.12162591516971588, "max": 3.490684747695923, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.82142857142856, "min": 351.82142857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29553.0, "min": 15984.0, "max": 32730.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6005523586202235, "min": -1.0000000521540642, "max": 1.6005523586202235, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.44639812409878, "min": -29.868201687932014, "max": 134.44639812409878, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6005523586202235, "min": -1.0000000521540642, "max": 1.6005523586202235, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.44639812409878, "min": -29.868201687932014, "max": 134.44639812409878, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031561698939358826, "min": 0.031561698939358826, "max": 9.716342358849943, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6511827109061414, "min": 2.6511827109061414, "max": 155.46147774159908, "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": "1723052083", "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": "1723054247" }, "total": 2163.9100334590003, "count": 1, "self": 0.834955999000158, "children": { "run_training.setup": { "total": 0.051194945999895936, "count": 1, "self": 0.051194945999895936 }, "TrainerController.start_learning": { "total": 2163.023882514, "count": 1, "self": 1.2303052740130624, "children": { "TrainerController._reset_env": { "total": 2.8953420630000437, "count": 1, "self": 2.8953420630000437 }, "TrainerController.advance": { "total": 2158.7623319969866, "count": 63763, "self": 1.2971556810812217, "children": { "env_step": { "total": 1529.584604795953, "count": 63763, "self": 1401.9134449739704, "children": { "SubprocessEnvManager._take_step": { "total": 126.91330017995779, "count": 63763, "self": 4.605758382931299, "children": { "TorchPolicy.evaluate": { "total": 122.30754179702649, "count": 62565, "self": 122.30754179702649 } } }, "workers": { "total": 0.7578596420248687, "count": 63763, "self": 0.0, "children": { "worker_root": { "total": 2158.240871837985, "count": 63763, "is_parallel": true, "self": 870.4975373350396, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004766347999975551, "count": 1, "is_parallel": true, "self": 0.0027739129998280987, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019924350001474522, "count": 8, "is_parallel": true, "self": 0.0019924350001474522 } } }, "UnityEnvironment.step": { "total": 0.07639488599988908, "count": 1, "is_parallel": true, "self": 0.0006350339999698917, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004902059999949415, "count": 1, "is_parallel": true, "self": 0.0004902059999949415 }, "communicator.exchange": { "total": 0.07368053400000463, "count": 1, "is_parallel": true, "self": 0.07368053400000463 }, "steps_from_proto": { "total": 0.0015891119999196235, "count": 1, "is_parallel": true, "self": 0.00033495399998173525, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012541579999378882, "count": 8, "is_parallel": true, "self": 0.0012541579999378882 } } } } } } }, "UnityEnvironment.step": { "total": 1287.7433345029456, "count": 63762, "is_parallel": true, "self": 32.35823698688091, "children": { "UnityEnvironment._generate_step_input": { "total": 22.235460456052124, "count": 63762, "is_parallel": true, "self": 22.235460456052124 }, "communicator.exchange": { "total": 1139.731884835002, "count": 63762, "is_parallel": true, "self": 1139.731884835002 }, "steps_from_proto": { "total": 93.41775222501064, "count": 63762, "is_parallel": true, "self": 18.282049098924745, "children": { "_process_rank_one_or_two_observation": { "total": 75.1357031260859, "count": 510096, "is_parallel": true, "self": 75.1357031260859 } } } } } } } } } } }, "trainer_advance": { "total": 627.8805715199526, "count": 63763, "self": 2.469118589024447, "children": { "process_trajectory": { "total": 125.10935570293032, "count": 63763, "self": 124.81535877593024, "children": { "RLTrainer._checkpoint": { "total": 0.2939969270000802, "count": 2, "self": 0.2939969270000802 } } }, "_update_policy": { "total": 500.3020972279978, "count": 451, "self": 296.18382941902564, "children": { "TorchPPOOptimizer.update": { "total": 204.11826780897218, "count": 22791, "self": 204.11826780897218 } } } } } } }, "trainer_threads": { "total": 1.362000148219522e-06, "count": 1, "self": 1.362000148219522e-06 }, "TrainerController._save_models": { "total": 0.13590181800009304, "count": 1, "self": 0.0019398370000089926, "children": { "RLTrainer._checkpoint": { "total": 0.13396198100008405, "count": 1, "self": 0.13396198100008405 } } } } } } }