{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28952282667160034, "min": 0.2659558057785034, "max": 1.4422105550765991, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8639.361328125, "min": 7995.6953125, "max": 43750.8984375, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45125919580459595, "min": -0.09791713207960129, "max": 0.6271527409553528, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.09627532958984, "min": -23.5980281829834, "max": 175.60276794433594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003893990069627762, "min": -0.017854563891887665, "max": 0.3102854788303375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.0708472728729248, "min": -4.9992780685424805, "max": 73.53765869140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07062288906749048, "min": 0.06528122935654171, "max": 0.07457379657162598, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9887204469448667, "min": 0.4756145981062156, "max": 1.060735726908509, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016151696381885336, "min": 0.000853100669201424, "max": 0.016151696381885336, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2261237493463947, "min": 0.01109030869961851, "max": 0.2261237493463947, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.703390289378568e-06, "min": 7.703390289378568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010784746405129996, "min": 0.00010784746405129996, "max": 0.0036326026891324997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025677642857143, "min": 0.1025677642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359487000000002, "min": 1.3886848, "max": 2.6108675000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000266519652142857, "min": 0.000266519652142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037312751299999987, "min": 0.0037312751299999987, "max": 0.12110566325000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010114679113030434, "min": 0.009164669550955296, "max": 0.28821802139282227, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14160551130771637, "min": 0.1283053755760193, "max": 2.017526149749756, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.0487804878049, "min": 333.9887640449438, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30344.0, "min": 15984.0, "max": 32638.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.434773152194372, "min": -1.0000000521540642, "max": 1.5536112170875742, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 117.6513984799385, "min": -30.669601671397686, "max": 138.2713983207941, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.434773152194372, "min": -1.0000000521540642, "max": 1.5536112170875742, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 117.6513984799385, "min": -30.669601671397686, "max": 138.2713983207941, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03904730620546971, "min": 0.03714026570218621, "max": 5.690149567089975, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.201879108848516, "min": 2.9031688054965343, "max": 91.0423930734396, "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": "1691184002", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691187204" }, "total": 3201.745813613, "count": 1, "self": 0.7077709270001833, "children": { "run_training.setup": { "total": 0.04749120299993592, "count": 1, "self": 0.04749120299993592 }, "TrainerController.start_learning": { "total": 3200.9905514829998, "count": 1, "self": 2.3399940409781266, "children": { "TrainerController._reset_env": { "total": 1.2807997039999464, "count": 1, "self": 1.2807997039999464 }, "TrainerController.advance": { "total": 3197.263485210021, "count": 63826, "self": 2.4062083860912935, "children": { "env_step": { "total": 2058.8560468929045, "count": 63826, "self": 1927.906057693795, "children": { "SubprocessEnvManager._take_step": { "total": 129.56786913710812, "count": 63826, "self": 6.543097361083028, "children": { "TorchPolicy.evaluate": { "total": 123.02477177602509, "count": 62551, "self": 123.02477177602509 } } }, "workers": { "total": 1.382120062001377, "count": 63826, "self": 0.0, "children": { "worker_root": { "total": 3194.4318334840123, "count": 63826, "is_parallel": true, "self": 1430.6641745709624, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002003309999963676, "count": 1, "is_parallel": true, "self": 0.0006103480002366268, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013929619997270493, "count": 8, "is_parallel": true, "self": 0.0013929619997270493 } } }, "UnityEnvironment.step": { "total": 0.061505890000034924, "count": 1, "is_parallel": true, "self": 0.0006846100002348976, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005819799998789676, "count": 1, "is_parallel": true, "self": 0.0005819799998789676 }, "communicator.exchange": { "total": 0.05802161599990541, "count": 1, "is_parallel": true, "self": 0.05802161599990541 }, "steps_from_proto": { "total": 0.0022176840000156517, "count": 1, "is_parallel": true, "self": 0.000454472000228634, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017632119997870177, "count": 8, "is_parallel": true, "self": 0.0017632119997870177 } } } } } } }, "UnityEnvironment.step": { "total": 1763.76765891305, "count": 63825, "is_parallel": true, "self": 46.140139396213726, "children": { "UnityEnvironment._generate_step_input": { "total": 25.433108590930487, "count": 63825, "is_parallel": true, "self": 25.433108590930487 }, "communicator.exchange": { "total": 1554.2651549569603, "count": 63825, "is_parallel": true, "self": 1554.2651549569603 }, "steps_from_proto": { "total": 137.92925596894543, "count": 63825, "is_parallel": true, "self": 28.575090253753388, "children": { "_process_rank_one_or_two_observation": { "total": 109.35416571519204, "count": 510600, "is_parallel": true, "self": 109.35416571519204 } } } } } } } } } } }, "trainer_advance": { "total": 1136.0012299310251, "count": 63826, "self": 4.085095686983777, "children": { "process_trajectory": { "total": 144.34740229504246, "count": 63826, "self": 144.11696526904257, "children": { "RLTrainer._checkpoint": { "total": 0.23043702599989047, "count": 2, "self": 0.23043702599989047 } } }, "_update_policy": { "total": 987.5687319489989, "count": 453, "self": 442.8723257139891, "children": { "TorchPPOOptimizer.update": { "total": 544.6964062350098, "count": 22764, "self": 544.6964062350098 } } } } } } }, "trainer_threads": { "total": 1.1430001904955134e-06, "count": 1, "self": 1.1430001904955134e-06 }, "TrainerController._save_models": { "total": 0.10627138500058209, "count": 1, "self": 0.0016504670011272538, "children": { "RLTrainer._checkpoint": { "total": 0.10462091799945483, "count": 1, "self": 0.10462091799945483 } } } } } } }