{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28527459502220154, "min": 0.28527459502220154, "max": 0.8091911673545837, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 285301.96875, "min": 285301.96875, "max": 809993.875, "count": 2 }, "Pyramids.Step.mean": { "value": 1999934.0, "min": 999945.0, "max": 1999934.0, "count": 2 }, "Pyramids.Step.sum": { "value": 1999934.0, "min": 999945.0, "max": 1999934.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7415024638175964, "min": 0.23188810050487518, "max": 0.7415024638175964, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 7183.67578125, "min": 1981.251953125, "max": 7183.67578125, "count": 2 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018552640452980995, "min": 0.018552640452980995, "max": 0.044761210680007935, "count": 2 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 179.73797607421875, "min": 179.73797607421875, "max": 382.4397888183594, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0698795911474811, "min": 0.06953028033090324, "max": 0.0698795911474811, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 33.053046612758564, "min": 31.497216989899165, "max": 33.053046612758564, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014082030205145302, "min": 0.00925891282502759, "max": 0.014082030205145302, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 6.660800287033728, "min": 4.1942875097374985, "max": 6.660800287033728, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001500183931228497, "min": 0.0001500183931228497, "max": 0.00024820753558645633, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0709586999471079, "min": 0.0709586999471079, "max": 0.11243801362066472, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15000611437632136, "min": 0.15000611437632136, "max": 0.18273583944076527, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 70.9528921, "min": 70.9528921, "max": 82.77933526666666, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.005005610826194503, "min": 0.005005610826194503, "max": 0.008275310360132451, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 2.36765392079, "min": 2.36765392079, "max": 3.7487155931400005, "count": 2 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009101846255362034, "min": 0.009101846255362034, "max": 0.03897382691502571, "count": 2 }, "Pyramids.Losses.RNDLoss.sum": { "value": 4.305173397064209, "min": 4.305173397064209, "max": 17.65514373779297, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 262.52948920484465, "min": 262.52948920484465, "max": 559.0589225589225, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 997087.0, "min": 996243.0, "max": 997087.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7121863454097725, "min": 0.8840585573211597, "max": 1.7121863454097725, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 6502.883739866316, "min": 1575.3923491463065, "max": 6502.883739866316, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7121863454097725, "min": 0.8840585573211597, "max": 1.7121863454097725, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 6502.883739866316, "min": 1575.3923491463065, "max": 6502.883739866316, "count": 2 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024821402965468867, "min": 0.024821402965468867, "max": 0.2895773124458181, "count": 2 }, "Pyramids.Policy.RndReward.sum": { "value": 94.27168846285076, "min": 94.27168846285076, "max": 516.0267707784478, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722964885", "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": "1722969631" }, "total": 4746.7302182290005, "count": 1, "self": 0.36047278200112487, "children": { "run_training.setup": { "total": 0.08770193399999471, "count": 1, "self": 0.08770193399999471 }, "TrainerController.start_learning": { "total": 4746.282043513, "count": 1, "self": 2.8767224388839168, "children": { "TrainerController._reset_env": { "total": 3.486408159000007, "count": 1, "self": 3.486408159000007 }, "TrainerController.advance": { "total": 4739.788283876114, "count": 130963, "self": 3.017240951126041, "children": { "env_step": { "total": 3445.560430220881, "count": 130963, "self": 3177.507715752776, "children": { "SubprocessEnvManager._take_step": { "total": 266.28681209310196, "count": 130963, "self": 9.440958887125305, "children": { "TorchPolicy.evaluate": { "total": 256.84585320597665, "count": 126593, "self": 256.84585320597665 } } }, "workers": { "total": 1.7659023750026677, "count": 130962, "self": 0.0, "children": { "worker_root": { "total": 4735.460590627047, "count": 130962, "is_parallel": true, "self": 1810.5629095971021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006372607000002972, "count": 1, "is_parallel": true, "self": 0.004408132000094156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019644749999088162, "count": 8, "is_parallel": true, "self": 0.0019644749999088162 } } }, "UnityEnvironment.step": { "total": 0.05322440300000153, "count": 1, "is_parallel": true, "self": 0.0006292960000564563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047906899999361485, "count": 1, "is_parallel": true, "self": 0.00047906899999361485 }, "communicator.exchange": { "total": 0.05045234599998594, "count": 1, "is_parallel": true, "self": 0.05045234599998594 }, "steps_from_proto": { "total": 0.001663691999965522, "count": 1, "is_parallel": true, "self": 0.00034139499996399536, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013222970000015266, "count": 8, "is_parallel": true, "self": 0.0013222970000015266 } } } } } } }, "UnityEnvironment.step": { "total": 2924.897681029945, "count": 130961, "is_parallel": true, "self": 67.92241027302589, "children": { "UnityEnvironment._generate_step_input": { "total": 46.63480053789914, "count": 130961, "is_parallel": true, "self": 46.63480053789914 }, "communicator.exchange": { "total": 2610.0097935539425, "count": 130961, "is_parallel": true, "self": 2610.0097935539425 }, "steps_from_proto": { "total": 200.33067666507753, "count": 130961, "is_parallel": true, "self": 41.29043980919806, "children": { "_process_rank_one_or_two_observation": { "total": 159.04023685587947, "count": 1047688, "is_parallel": true, "self": 159.04023685587947 } } } } } } } } } } }, "trainer_advance": { "total": 1291.2106127041072, "count": 130962, "self": 5.662005640152302, "children": { "process_trajectory": { "total": 270.204904544953, "count": 130962, "self": 269.6615942329531, "children": { "RLTrainer._checkpoint": { "total": 0.5433103119999032, "count": 4, "self": 0.5433103119999032 } } }, "_update_policy": { "total": 1015.343702519002, "count": 938, "self": 602.1884241310223, "children": { "TorchPPOOptimizer.update": { "total": 413.1552783879797, "count": 46137, "self": 413.1552783879797 } } } } } } }, "trainer_threads": { "total": 1.32000059238635e-06, "count": 1, "self": 1.32000059238635e-06 }, "TrainerController._save_models": { "total": 0.13062771900058578, "count": 1, "self": 0.0021128799999132752, "children": { "RLTrainer._checkpoint": { "total": 0.1285148390006725, "count": 1, "self": 0.1285148390006725 } } } } } } }