{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3717065155506134, "min": 0.3717065155506134, "max": 1.430887222290039, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 9307.53125, "min": 9307.53125, "max": 37546.48046875, "count": 40 }, "Pyramids.Step.mean": { "value": 999880.0, "min": 24960.0, "max": 999880.0, "count": 40 }, "Pyramids.Step.sum": { "value": 999880.0, "min": 24960.0, "max": 999880.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41443079710006714, "min": -0.10167810320854187, "max": 0.4854196608066559, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 91.58920288085938, "min": -20.640655517578125, "max": 111.16110229492188, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.031095504760742188, "min": -0.031095504760742188, "max": 0.6881605982780457, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.872106552124023, "min": -6.872106552124023, "max": 136.25579833984375, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07036561959407338, "min": 0.06499400433110873, "max": 0.07666250546844228, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8443874351288805, "min": 0.43218180214372015, "max": 0.9199500656213073, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019928521640799265, "min": 0.0009607693363056746, "max": 0.022744881211312736, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23914225968959119, "min": 0.011529232035668096, "max": 0.25626501733980456, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.6447987851e-06, "min": 3.6447987851e-06, "max": 0.0002957568014144, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.37375854212e-05, "min": 4.37375854212e-05, "max": 0.0030127633957456003, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1012149, "min": 0.1012149, "max": 0.1985856, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2145788, "min": 1.1915136, "max": 2.2042544, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013136851000000003, "min": 0.00013136851000000003, "max": 0.00985870144, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015764221200000002, "min": 0.0015764221200000002, "max": 0.10044501455999999, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010496657341718674, "min": 0.010496657341718674, "max": 0.7131252884864807, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12595988810062408, "min": 0.12595988810062408, "max": 4.278751850128174, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 448.3888888888889, "min": 395.12307692307695, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 24213.0, "min": 15984.0, "max": 31780.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4404555325982746, "min": -1.0000000521540642, "max": 1.5448687304742634, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.78459876030684, "min": -25.428201369941235, "max": 98.87159875035286, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4404555325982746, "min": -1.0000000521540642, "max": 1.5448687304742634, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.78459876030684, "min": -25.428201369941235, "max": 98.87159875035286, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04927700894067702, "min": 0.0477619415864865, "max": 13.462835285812616, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.660958482796559, "min": 2.660958482796559, "max": 215.40536457300186, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674856019", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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 --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674857962" }, "total": 1942.2972861010003, "count": 1, "self": 0.43980481600010535, "children": { "run_training.setup": { "total": 0.10865098000067519, "count": 1, "self": 0.10865098000067519 }, "TrainerController.start_learning": { "total": 1941.7488303049995, "count": 1, "self": 1.191357165154841, "children": { "TrainerController._reset_env": { "total": 6.082586245998755, "count": 1, "self": 6.082586245998755 }, "TrainerController.advance": { "total": 1934.3904404408477, "count": 63600, "self": 1.2789828085369663, "children": { "env_step": { "total": 1300.343419136154, "count": 63600, "self": 1198.7808846901717, "children": { "SubprocessEnvManager._take_step": { "total": 100.8517639030706, "count": 63600, "self": 4.167788762069904, "children": { "TorchPolicy.evaluate": { "total": 96.6839751410007, "count": 62561, "self": 32.70647794299657, "children": { "TorchPolicy.sample_actions": { "total": 63.97749719800413, "count": 62561, "self": 63.97749719800413 } } } } }, "workers": { "total": 0.7107705429116322, "count": 63600, "self": 0.0, "children": { "worker_root": { "total": 1938.763565574236, "count": 63600, "is_parallel": true, "self": 833.9372392900605, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00218982899968978, "count": 1, "is_parallel": true, "self": 0.0006793419997848105, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015104869999049697, "count": 8, "is_parallel": true, "self": 0.0015104869999049697 } } }, "UnityEnvironment.step": { "total": 0.04978918400047405, "count": 1, "is_parallel": true, "self": 0.0005026150010962738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042240200127707794, "count": 1, "is_parallel": true, "self": 0.00042240200127707794 }, "communicator.exchange": { "total": 0.04629751899847179, "count": 1, "is_parallel": true, "self": 0.04629751899847179 }, "steps_from_proto": { "total": 0.0025666479996289127, "count": 1, "is_parallel": true, "self": 0.00041086700184678193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021557809977821307, "count": 8, "is_parallel": true, "self": 0.0021557809977821307 } } } } } } }, "UnityEnvironment.step": { "total": 1104.8263262841756, "count": 63599, "is_parallel": true, "self": 26.895105019448238, "children": { "UnityEnvironment._generate_step_input": { "total": 20.938269342976128, "count": 63599, "is_parallel": true, "self": 20.938269342976128 }, "communicator.exchange": { "total": 970.4931489759856, "count": 63599, "is_parallel": true, "self": 970.4931489759856 }, "steps_from_proto": { "total": 86.49980294576562, "count": 63599, "is_parallel": true, "self": 20.16335105710823, "children": { "_process_rank_one_or_two_observation": { "total": 66.3364518886574, "count": 508792, "is_parallel": true, "self": 66.3364518886574 } } } } } } } } } } }, "trainer_advance": { "total": 632.7680384961568, "count": 63600, "self": 2.2781849887360295, "children": { "process_trajectory": { "total": 137.97919158540572, "count": 63600, "self": 137.79304402640446, "children": { "RLTrainer._checkpoint": { "total": 0.186147559001256, "count": 2, "self": 0.186147559001256 } } }, "_update_policy": { "total": 492.51066192201506, "count": 459, "self": 180.62755583808212, "children": { "TorchPPOOptimizer.update": { "total": 311.88310608393294, "count": 22794, "self": 311.88310608393294 } } } } } } }, "trainer_threads": { "total": 8.819988579489291e-07, "count": 1, "self": 8.819988579489291e-07 }, "TrainerController._save_models": { "total": 0.0844455709993781, "count": 1, "self": 0.00227843200082134, "children": { "RLTrainer._checkpoint": { "total": 0.08216713899855677, "count": 1, "self": 0.08216713899855677 } } } } } } }