{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6198543310165405, "min": 0.6181684136390686, "max": 1.4397516250610352, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18704.724609375, "min": 18426.36328125, "max": 43676.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989919.0, "min": 29952.0, "max": 989919.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20321184396743774, "min": -0.1136462390422821, "max": 0.2698386013507843, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 51.615806579589844, "min": -27.275096893310547, "max": 69.61836242675781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.3597458302974701, "min": -0.3597458302974701, "max": 0.2695969045162201, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -91.37544250488281, "min": -91.37544250488281, "max": 64.70325469970703, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0710423098076024, "min": 0.06481601432117969, "max": 0.07412011613098765, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9945923373064336, "min": 0.47087696331905077, "max": 1.0567155789912623, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.039052608103832306, "min": 0.00016720261613035686, "max": 0.039052608103832306, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5467365134536523, "min": 0.002340836625824996, "max": 0.5467365134536523, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.65005459287143e-06, "min": 7.65005459287143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010710076430020003, "min": 0.00010710076430020003, "max": 0.003507054230982, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254998571428572, "min": 0.10254998571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356998, "min": 1.3691136000000002, "max": 2.5690179999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000264743572857143, "min": 0.000264743572857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037064100200000023, "min": 0.0037064100200000023, "max": 0.1169248982, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010702558793127537, "min": 0.010649963282048702, "max": 0.4051334857940674, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14983582496643066, "min": 0.14983582496643066, "max": 2.8359344005584717, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 590.7021276595744, "min": 557.08, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27763.0, "min": 15984.0, "max": 33052.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.026191457313426, "min": -1.0000000521540642, "max": 1.082807960063219, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 48.23099849373102, "min": -32.000001668930054, "max": 54.14039800316095, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.026191457313426, "min": -1.0000000521540642, "max": 1.082807960063219, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 48.23099849373102, "min": -32.000001668930054, "max": 54.14039800316095, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06640417896585163, "min": 0.06490983254687828, "max": 7.933333176188171, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1209964113950264, "min": 3.1209964113950264, "max": 126.93333081901073, "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": "1719354078", "python_version": "3.10.12 (main, Jun 25 2024, 18:12:47) [GCC 14.1.1 20240522]", "command_line_arguments": "/home/matt/docs/howTo/ai/u5/hf-env/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining1 --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": "1719354850" }, "total": 772.2147408680012, "count": 1, "self": 0.21933395199994266, "children": { "run_training.setup": { "total": 0.00818785800038313, "count": 1, "self": 0.00818785800038313 }, "TrainerController.start_learning": { "total": 771.9872190580008, "count": 1, "self": 0.7863086638917594, "children": { "TrainerController._reset_env": { "total": 1.1219685710002523, "count": 1, "self": 1.1219685710002523 }, "TrainerController.advance": { "total": 770.0380192641078, "count": 63306, "self": 0.7409733681888611, "children": { "env_step": { "total": 494.03147631499996, "count": 63306, "self": 436.92875950705275, "children": { "SubprocessEnvManager._take_step": { "total": 56.58980958004031, "count": 63306, "self": 2.445062810993477, "children": { "TorchPolicy.evaluate": { "total": 54.14474676904683, "count": 62559, "self": 54.14474676904683 } } }, "workers": { "total": 0.5129072279069078, "count": 63306, "self": 0.0, "children": { "worker_root": { "total": 770.9131181956782, "count": 63306, "is_parallel": true, "self": 389.37936747566346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001608086000487674, "count": 1, "is_parallel": true, "self": 0.0005663340034516295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010417519970360445, "count": 8, "is_parallel": true, "self": 0.0010417519970360445 } } }, "UnityEnvironment.step": { "total": 0.019292205000965623, "count": 1, "is_parallel": true, "self": 0.00030818700179224834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002608859995234525, "count": 1, "is_parallel": true, "self": 0.0002608859995234525 }, "communicator.exchange": { "total": 0.017637499000557, "count": 1, "is_parallel": true, "self": 0.017637499000557 }, "steps_from_proto": { "total": 0.0010856329990929225, "count": 1, "is_parallel": true, "self": 0.00025549399651936255, "children": { "_process_rank_one_or_two_observation": { "total": 0.00083013900257356, "count": 8, "is_parallel": true, "self": 0.00083013900257356 } } } } } } }, "UnityEnvironment.step": { "total": 381.5337507200147, "count": 63305, "is_parallel": true, "self": 10.501863388253696, "children": { "UnityEnvironment._generate_step_input": { "total": 7.007109749909432, "count": 63305, "is_parallel": true, "self": 7.007109749909432 }, "communicator.exchange": { "total": 332.8179504499112, "count": 63305, "is_parallel": true, "self": 332.8179504499112 }, "steps_from_proto": { "total": 31.206827131940372, "count": 63305, "is_parallel": true, "self": 6.654570320828498, "children": { "_process_rank_one_or_two_observation": { "total": 24.552256811111874, "count": 506440, "is_parallel": true, "self": 24.552256811111874 } } } } } } } } } } }, "trainer_advance": { "total": 275.26556958091896, "count": 63306, "self": 1.3477594488267641, "children": { "process_trajectory": { "total": 56.49142784509422, "count": 63306, "self": 56.40052474509321, "children": { "RLTrainer._checkpoint": { "total": 0.09090310000101454, "count": 2, "self": 0.09090310000101454 } } }, "_update_policy": { "total": 217.42638228699798, "count": 442, "self": 141.62483508419973, "children": { "TorchPPOOptimizer.update": { "total": 75.80154720279825, "count": 22779, "self": 75.80154720279825 } } } } } } }, "trainer_threads": { "total": 5.150013748789206e-07, "count": 1, "self": 5.150013748789206e-07 }, "TrainerController._save_models": { "total": 0.04092204399967159, "count": 1, "self": 0.00048346999938075896, "children": { "RLTrainer._checkpoint": { "total": 0.04043857400029083, "count": 1, "self": 0.04043857400029083 } } } } } } }