{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7147308588027954, "min": 0.7079724669456482, "max": 1.4844430685043335, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21613.4609375, "min": 21227.845703125, "max": 45032.06640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989997.0, "min": 29952.0, "max": 989997.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2285950481891632, "min": -0.11240927875041962, "max": 0.2285950481891632, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 58.97752380371094, "min": -26.978227615356445, "max": 58.97752380371094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003648479701951146, "min": -0.00467608030885458, "max": 0.23512747883796692, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.941307783126831, "min": -1.15966796875, "max": 56.66572189331055, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06774052832694985, "min": 0.06429839648748119, "max": 0.07301655005495476, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9483673965772978, "min": 0.49004566178328607, "max": 1.0952482508243215, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010697572150755416, "min": 7.263555975473255e-05, "max": 0.010697572150755416, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14976601011057583, "min": 0.0009442622768115232, "max": 0.14976601011057583, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.741875990835719e-06, "min": 7.741875990835719e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010838626387170006, "min": 0.00010838626387170006, "max": 0.0033816884727705995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258059285714285, "min": 0.10258059285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361283, "min": 1.3886848, "max": 2.5272294000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002678012264285715, "min": 0.0002678012264285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003749217170000001, "min": 0.003749217170000001, "max": 0.11275021705999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011644708923995495, "min": 0.011621871963143349, "max": 0.5567595362663269, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16302593052387238, "min": 0.16270621120929718, "max": 3.8973169326782227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 625.6041666666666, "min": 625.6041666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30029.0, "min": 15984.0, "max": 33250.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9159249681979418, "min": -1.0000000521540642, "max": 0.9159249681979418, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 43.964398473501205, "min": -31.99640168249607, "max": 43.964398473501205, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9159249681979418, "min": -1.0000000521540642, "max": 0.9159249681979418, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 43.964398473501205, "min": -31.99640168249607, "max": 43.964398473501205, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07582981023006141, "min": 0.07582981023006141, "max": 11.688260393217206, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6398308910429478, "min": 3.4856854253448546, "max": 187.0121662914753, "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": "1727347446", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727351200" }, "total": 3753.6502598119996, "count": 1, "self": 0.6821211519991266, "children": { "run_training.setup": { "total": 0.07976908700015883, "count": 1, "self": 0.07976908700015883 }, "TrainerController.start_learning": { "total": 3752.888369573, "count": 1, "self": 3.0059257990014885, "children": { "TrainerController._reset_env": { "total": 2.8383892730000753, "count": 1, "self": 2.8383892730000753 }, "TrainerController.advance": { "total": 3746.953307278999, "count": 63260, "self": 3.1412322570408833, "children": { "env_step": { "total": 2415.139515461032, "count": 63260, "self": 2200.7579430119836, "children": { "SubprocessEnvManager._take_step": { "total": 212.6228228550617, "count": 63260, "self": 9.689929285989592, "children": { "TorchPolicy.evaluate": { "total": 202.93289356907212, "count": 62563, "self": 202.93289356907212 } } }, "workers": { "total": 1.758749593986522, "count": 63260, "self": 0.0, "children": { "worker_root": { "total": 3744.0942890999254, "count": 63260, "is_parallel": true, "self": 1777.257499567988, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003582511999866256, "count": 1, "is_parallel": true, "self": 0.001298630000292178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022838819995740778, "count": 8, "is_parallel": true, "self": 0.0022838819995740778 } } }, "UnityEnvironment.step": { "total": 0.07741836200011676, "count": 1, "is_parallel": true, "self": 0.0009192710001570958, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006236579999949754, "count": 1, "is_parallel": true, "self": 0.0006236579999949754 }, "communicator.exchange": { "total": 0.07349305499997172, "count": 1, "is_parallel": true, "self": 0.07349305499997172 }, "steps_from_proto": { "total": 0.0023823779999929684, "count": 1, "is_parallel": true, "self": 0.0005313999995451013, "children": { "_process_rank_one_or_two_observation": { "total": 0.001850978000447867, "count": 8, "is_parallel": true, "self": 0.001850978000447867 } } } } } } }, "UnityEnvironment.step": { "total": 1966.8367895319375, "count": 63259, "is_parallel": true, "self": 59.56995840684954, "children": { "UnityEnvironment._generate_step_input": { "total": 34.679563953102615, "count": 63259, "is_parallel": true, "self": 34.679563953102615 }, "communicator.exchange": { "total": 1728.4286373339664, "count": 63259, "is_parallel": true, "self": 1728.4286373339664 }, "steps_from_proto": { "total": 144.1586298380189, "count": 63259, "is_parallel": true, "self": 32.896038669710606, "children": { "_process_rank_one_or_two_observation": { "total": 111.26259116830829, "count": 506072, "is_parallel": true, "self": 111.26259116830829 } } } } } } } } } } }, "trainer_advance": { "total": 1328.6725595609264, "count": 63260, "self": 6.218356581976877, "children": { "process_trajectory": { "total": 206.99480051295222, "count": 63260, "self": 206.71308506095238, "children": { "RLTrainer._checkpoint": { "total": 0.28171545199984394, "count": 2, "self": 0.28171545199984394 } } }, "_update_policy": { "total": 1115.4594024659973, "count": 442, "self": 434.1012715350048, "children": { "TorchPPOOptimizer.update": { "total": 681.3581309309925, "count": 22779, "self": 681.3581309309925 } } } } } } }, "trainer_threads": { "total": 1.5830000847927295e-06, "count": 1, "self": 1.5830000847927295e-06 }, "TrainerController._save_models": { "total": 0.09074563899957866, "count": 1, "self": 0.002451888999530638, "children": { "RLTrainer._checkpoint": { "total": 0.08829375000004802, "count": 1, "self": 0.08829375000004802 } } } } } } }