{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8829163312911987, "min": 0.5154019594192505, "max": 1.320285439491272, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 26445.109375, "min": 15561.0166015625, "max": 40052.1796875, "count": 30 }, "Pyramids.Step.mean": { "value": 899896.0, "min": 29941.0, "max": 899896.0, "count": 30 }, "Pyramids.Step.sum": { "value": 899896.0, "min": 29941.0, "max": 899896.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00843646191060543, "min": -0.11877094209194183, "max": 0.07134663313627243, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -2.0331873893737793, "min": -28.623796463012695, "max": 17.76531219482422, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17554783821105957, "min": 0.05362718552350998, "max": 0.7623623013496399, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 42.307029724121094, "min": 13.03140640258789, "max": 183.72930908203125, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.029620188957085784, "min": 0.027056231224421586, "max": 0.03839687915910099, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.41468264539920097, "min": 0.26642437374296907, "max": 0.49645410004692775, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01609308719794388, "min": 0.0003392493478410567, "max": 0.023705348556783672, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2253032207712143, "min": 0.004749490869774794, "max": 0.33187487979497143, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.279003002269848e-06, "min": 5.279003002269848e-06, "max": 0.000294611811319873, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.390604203177787e-05, "min": 7.390604203177787e-05, "max": 0.003291399969533445, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10175963492063493, "min": 0.10175963492063493, "max": 0.1982039365079365, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4246348888888891, "min": 1.3874275555555555, "max": 2.4971332222222227, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001857875285714288, "min": 0.0001857875285714288, "max": 0.009820573257142858, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.002601025400000003, "min": 0.002601025400000003, "max": 0.10974360890000001, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.027347082272171974, "min": 0.027347082272171974, "max": 0.9526971578598022, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.38285914063453674, "min": 0.38285914063453674, "max": 6.668879985809326, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 931.0588235294117, "min": 695.0243902439024, "max": 999.0, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31656.0, "min": 16868.0, "max": 33579.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5198235796654925, "min": -0.9997448800452824, "max": 0.2803072807628934, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.674001708626747, "min": -30.209601677954197, "max": 11.49259851127863, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5198235796654925, "min": -0.9997448800452824, "max": 0.2803072807628934, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.674001708626747, "min": -30.209601677954197, "max": 11.49259851127863, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2565415463382926, "min": 0.21640186110034404, "max": 9.653701529783362, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 8.722412575501949, "min": 8.623149914696114, "max": 267.2426235154271, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675844784", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675847515" }, "total": 2731.713949136, "count": 1, "self": 1.571031180999853, "children": { "run_training.setup": { "total": 0.1411415580000721, "count": 1, "self": 0.1411415580000721 }, "TrainerController.start_learning": { "total": 2730.001776397, "count": 1, "self": 1.9989818709523206, "children": { "TrainerController._reset_env": { "total": 4.877051002999906, "count": 1, "self": 4.877051002999906 }, "TrainerController.advance": { "total": 2722.964346323048, "count": 56921, "self": 2.363525683246735, "children": { "env_step": { "total": 1816.9700601798286, "count": 56921, "self": 1690.1874560876581, "children": { "SubprocessEnvManager._take_step": { "total": 125.44141648308369, "count": 56921, "self": 5.824274850137954, "children": { "TorchPolicy.evaluate": { "total": 119.61714163294573, "count": 56305, "self": 26.035691568941274, "children": { "TorchPolicy.sample_actions": { "total": 93.58145006400446, "count": 56305, "self": 93.58145006400446 } } } } }, "workers": { "total": 1.3411876090867736, "count": 56921, "self": 0.0, "children": { "worker_root": { "total": 2723.8266814189706, "count": 56921, "is_parallel": true, "self": 1190.9411453369726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025363949998791213, "count": 1, "is_parallel": true, "self": 0.0008925879997150332, "children": { "_process_rank_one_or_two_observation": { "total": 0.001643807000164088, "count": 8, "is_parallel": true, "self": 0.001643807000164088 } } }, "UnityEnvironment.step": { "total": 0.12235418000000209, "count": 1, "is_parallel": true, "self": 0.0007234530007735884, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005212759997448302, "count": 1, "is_parallel": true, "self": 0.0005212759997448302 }, "communicator.exchange": { "total": 0.11095716799991351, "count": 1, "is_parallel": true, "self": 0.11095716799991351 }, "steps_from_proto": { "total": 0.010152282999570161, "count": 1, "is_parallel": true, "self": 0.0005948379998699238, "children": { "_process_rank_one_or_two_observation": { "total": 0.009557444999700238, "count": 8, "is_parallel": true, "self": 0.009557444999700238 } } } } } } }, "UnityEnvironment.step": { "total": 1532.885536081998, "count": 56920, "is_parallel": true, "self": 40.45352455612783, "children": { "UnityEnvironment._generate_step_input": { "total": 23.107096253947475, "count": 56920, "is_parallel": true, "self": 23.107096253947475 }, "communicator.exchange": { "total": 1338.4872392230154, "count": 56920, "is_parallel": true, "self": 1338.4872392230154 }, "steps_from_proto": { "total": 130.83767604890727, "count": 56920, "is_parallel": true, "self": 30.789927211095346, "children": { "_process_rank_one_or_two_observation": { "total": 100.04774883781192, "count": 455360, "is_parallel": true, "self": 100.04774883781192 } } } } } } } } } } }, "trainer_advance": { "total": 903.6307604599729, "count": 56921, "self": 3.8528607869684492, "children": { "process_trajectory": { "total": 193.34497232800595, "count": 56921, "self": 193.2433500370057, "children": { "RLTrainer._checkpoint": { "total": 0.10162229100023978, "count": 1, "self": 0.10162229100023978 } } }, "_update_policy": { "total": 706.4329273449985, "count": 398, "self": 245.46006338500183, "children": { "TorchPPOOptimizer.update": { "total": 460.97286395999663, "count": 5046, "self": 460.97286395999663 } } } } } } }, "trainer_threads": { "total": 1.3389999367063865e-06, "count": 1, "self": 1.3389999367063865e-06 }, "TrainerController._save_models": { "total": 0.1613958609996189, "count": 1, "self": 0.002563572999861208, "children": { "RLTrainer._checkpoint": { "total": 0.15883228799975768, "count": 1, "self": 0.15883228799975768 } } } } } } }