{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4806901514530182, "min": 0.46457338333129883, "max": 1.509286642074585, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14305.3388671875, "min": 13989.2333984375, "max": 45785.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46322131156921387, "min": -0.10201238095760345, "max": 0.5155754685401917, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 126.92263793945312, "min": -24.48297119140625, "max": 140.2365264892578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04039676859974861, "min": -0.04039676859974861, "max": 0.3379466235637665, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.068714141845703, "min": -11.068714141845703, "max": 80.09335327148438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07026558325938027, "min": 0.06552534022972417, "max": 0.07484890726426109, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9837181656313237, "min": 0.5239423508498277, "max": 1.08966584711258, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015307872783844632, "min": 0.00011374262652312138, "max": 0.015307872783844632, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21431021897382485, "min": 0.0015923967713236994, "max": 0.21431021897382485, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.467890367878568e-06, "min": 7.467890367878568e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010455046515029996, "min": 0.00010455046515029996, "max": 0.0035069090310304, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248926428571428, "min": 0.10248926428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348497, "min": 1.3886848, "max": 2.5689696, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025867750214285704, "min": 0.00025867750214285704, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003621485029999999, "min": 0.003621485029999999, "max": 0.11692006304000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011027449741959572, "min": 0.011027449741959572, "max": 0.3329103887081146, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1543843001127243, "min": 0.1543843001127243, "max": 2.3303728103637695, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 360.4634146341463, "min": 360.4634146341463, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29558.0, "min": 15984.0, "max": 32657.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5663438861871637, "min": -1.0000000521540642, "max": 1.5663438861871637, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.44019866734743, "min": -31.998001664876938, "max": 128.44019866734743, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5663438861871637, "min": -1.0000000521540642, "max": 1.5663438861871637, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.44019866734743, "min": -31.998001664876938, "max": 128.44019866734743, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04146373877301812, "min": 0.04146373877301812, "max": 6.50433171633631, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.400026579387486, "min": 3.242724022711627, "max": 104.06930746138096, "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": "1690391517", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690393612" }, "total": 2095.1060870580004, "count": 1, "self": 0.48681907499985755, "children": { "run_training.setup": { "total": 0.031005214000288106, "count": 1, "self": 0.031005214000288106 }, "TrainerController.start_learning": { "total": 2094.5882627690003, "count": 1, "self": 1.32669109706967, "children": { "TrainerController._reset_env": { "total": 4.0577858370002104, "count": 1, "self": 4.0577858370002104 }, "TrainerController.advance": { "total": 2089.1086285639294, "count": 63463, "self": 1.3698474590592014, "children": { "env_step": { "total": 1438.4763797010228, "count": 63463, "self": 1331.8593100960966, "children": { "SubprocessEnvManager._take_step": { "total": 105.79417967197196, "count": 63463, "self": 4.595622309030205, "children": { "TorchPolicy.evaluate": { "total": 101.19855736294176, "count": 62555, "self": 101.19855736294176 } } }, "workers": { "total": 0.8228899329542401, "count": 63463, "self": 0.0, "children": { "worker_root": { "total": 2089.7320063191414, "count": 63463, "is_parallel": true, "self": 868.0056213691682, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017073590001928096, "count": 1, "is_parallel": true, "self": 0.000550068000848114, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011572909993446956, "count": 8, "is_parallel": true, "self": 0.0011572909993446956 } } }, "UnityEnvironment.step": { "total": 0.04772115900004792, "count": 1, "is_parallel": true, "self": 0.0005641980005748337, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004791829996975139, "count": 1, "is_parallel": true, "self": 0.0004791829996975139 }, "communicator.exchange": { "total": 0.04492968300019129, "count": 1, "is_parallel": true, "self": 0.04492968300019129 }, "steps_from_proto": { "total": 0.001748094999584282, "count": 1, "is_parallel": true, "self": 0.0003509819989631069, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013971130006211752, "count": 8, "is_parallel": true, "self": 0.0013971130006211752 } } } } } } }, "UnityEnvironment.step": { "total": 1221.7263849499732, "count": 63462, "is_parallel": true, "self": 33.59547664998672, "children": { "UnityEnvironment._generate_step_input": { "total": 22.947498263910347, "count": 63462, "is_parallel": true, "self": 22.947498263910347 }, "communicator.exchange": { "total": 1066.7790750650006, "count": 63462, "is_parallel": true, "self": 1066.7790750650006 }, "steps_from_proto": { "total": 98.40433497107551, "count": 63462, "is_parallel": true, "self": 19.753276786021615, "children": { "_process_rank_one_or_two_observation": { "total": 78.6510581850539, "count": 507696, "is_parallel": true, "self": 78.6510581850539 } } } } } } } } } } }, "trainer_advance": { "total": 649.2624014038474, "count": 63463, "self": 2.343993215905357, "children": { "process_trajectory": { "total": 105.70728281793299, "count": 63463, "self": 105.50124141793367, "children": { "RLTrainer._checkpoint": { "total": 0.20604139999932158, "count": 2, "self": 0.20604139999932158 } } }, "_update_policy": { "total": 541.2111253700091, "count": 444, "self": 353.88759886308753, "children": { "TorchPPOOptimizer.update": { "total": 187.32352650692155, "count": 22815, "self": 187.32352650692155 } } } } } } }, "trainer_threads": { "total": 8.140004865708761e-07, "count": 1, "self": 8.140004865708761e-07 }, "TrainerController._save_models": { "total": 0.0951564570004848, "count": 1, "self": 0.0013648860003740992, "children": { "RLTrainer._checkpoint": { "total": 0.09379157100011071, "count": 1, "self": 0.09379157100011071 } } } } } } }