{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6118618249893188, "min": 0.6118618249893188, "max": 1.350052833557129, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18336.275390625, "min": 18336.275390625, "max": 40955.203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3140895664691925, "min": -0.10031775385141373, "max": 0.31512054800987244, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 81.34919738769531, "min": -24.176578521728516, "max": 81.93134307861328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1363905668258667, "min": -0.015792928636074066, "max": 0.5818384289741516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 35.325157165527344, "min": -4.042989730834961, "max": 137.8957061767578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06779430127930594, "min": 0.06499102802026757, "max": 0.07745201922210912, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9491202179102832, "min": 0.5072966239290665, "max": 1.056646689355451, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01327134860249961, "min": 0.00017275327447076216, "max": 0.013517837692190714, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18579888043499454, "min": 0.0024185458425906702, "max": 0.18924972769067, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.586347471249999e-06, "min": 7.586347471249999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010620886459749998, "min": 0.00010620886459749998, "max": 0.0036334780888406994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252874999999999, "min": 0.10252874999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354025, "min": 1.3886848, "max": 2.6111593, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262622125, "min": 0.000262622125, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036767097500000003, "min": 0.0036767097500000003, "max": 0.12113481407, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013400733470916748, "min": 0.013400733470916748, "max": 0.43118879199028015, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18761026859283447, "min": 0.18761026859283447, "max": 3.0183215141296387, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 528.9298245614035, "min": 528.9298245614035, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30149.0, "min": 15984.0, "max": 32833.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2253999689169097, "min": -1.0000000521540642, "max": 1.2253999689169097, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 69.84779822826385, "min": -30.344601705670357, "max": 69.84779822826385, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2253999689169097, "min": -1.0000000521540642, "max": 1.2253999689169097, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 69.84779822826385, "min": -30.344601705670357, "max": 69.84779822826385, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0741459309208215, "min": 0.0741459309208215, "max": 9.0309820715338, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.2263180624868255, "min": 4.191420782124624, "max": 144.4957131445408, "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": "1680036382", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680038732" }, "total": 2350.146575615, "count": 1, "self": 0.48700079999980517, "children": { "run_training.setup": { "total": 0.10729845100013335, "count": 1, "self": 0.10729845100013335 }, "TrainerController.start_learning": { "total": 2349.552276364, "count": 1, "self": 1.6887959779719495, "children": { "TrainerController._reset_env": { "total": 8.79367004300002, "count": 1, "self": 8.79367004300002 }, "TrainerController.advance": { "total": 2338.967021472028, "count": 63347, "self": 1.8508574250740821, "children": { "env_step": { "total": 1672.0562447709865, "count": 63347, "self": 1544.7482636068937, "children": { "SubprocessEnvManager._take_step": { "total": 126.32351542799643, "count": 63347, "self": 5.261888127013663, "children": { "TorchPolicy.evaluate": { "total": 121.06162730098276, "count": 62571, "self": 121.06162730098276 } } }, "workers": { "total": 0.9844657360963538, "count": 63347, "self": 0.0, "children": { "worker_root": { "total": 2343.66529431901, "count": 63347, "is_parallel": true, "self": 932.4608729579661, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022863320000396925, "count": 1, "is_parallel": true, "self": 0.0007311019996905088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015552300003491837, "count": 8, "is_parallel": true, "self": 0.0015552300003491837 } } }, "UnityEnvironment.step": { "total": 0.07719553299989457, "count": 1, "is_parallel": true, "self": 0.0005155250000825617, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048210799991466047, "count": 1, "is_parallel": true, "self": 0.00048210799991466047 }, "communicator.exchange": { "total": 0.07212041899992983, "count": 1, "is_parallel": true, "self": 0.07212041899992983 }, "steps_from_proto": { "total": 0.00407748099996752, "count": 1, "is_parallel": true, "self": 0.0005706899996766879, "children": { "_process_rank_one_or_two_observation": { "total": 0.003506791000290832, "count": 8, "is_parallel": true, "self": 0.003506791000290832 } } } } } } }, "UnityEnvironment.step": { "total": 1411.204421361044, "count": 63346, "is_parallel": true, "self": 32.80520712202815, "children": { "UnityEnvironment._generate_step_input": { "total": 23.54537334501788, "count": 63346, "is_parallel": true, "self": 23.54537334501788 }, "communicator.exchange": { "total": 1258.2587874370133, "count": 63346, "is_parallel": true, "self": 1258.2587874370133 }, "steps_from_proto": { "total": 96.59505345698472, "count": 63346, "is_parallel": true, "self": 21.212994854110093, "children": { "_process_rank_one_or_two_observation": { "total": 75.38205860287462, "count": 506768, "is_parallel": true, "self": 75.38205860287462 } } } } } } } } } } }, "trainer_advance": { "total": 665.0599192759676, "count": 63347, "self": 3.1000753229016027, "children": { "process_trajectory": { "total": 125.33956371206273, "count": 63347, "self": 125.12561293206295, "children": { "RLTrainer._checkpoint": { "total": 0.2139507799997773, "count": 2, "self": 0.2139507799997773 } } }, "_update_policy": { "total": 536.6202802410032, "count": 452, "self": 341.7942142610184, "children": { "TorchPPOOptimizer.update": { "total": 194.82606597998483, "count": 22773, "self": 194.82606597998483 } } } } } } }, "trainer_threads": { "total": 8.320002962136641e-07, "count": 1, "self": 8.320002962136641e-07 }, "TrainerController._save_models": { "total": 0.10278803899973354, "count": 1, "self": 0.0013622399997075263, "children": { "RLTrainer._checkpoint": { "total": 0.10142579900002602, "count": 1, "self": 0.10142579900002602 } } } } } } }