NBKi's picture
Second Push
154551d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7335434556007385,
"min": 0.7335434556007385,
"max": 2.8903188705444336,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7512.21826171875,
"min": 6999.51611328125,
"max": 29917.69140625,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.804928779602051,
"min": -0.0671207457780838,
"max": 2.804928779602051,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 575.0103759765625,
"min": -13.021425247192383,
"max": 575.0103759765625,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 11343.0,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.87272727272727,
"min": 2.3863636363636362,
"max": 28.2,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1533.0,
"min": 105.0,
"max": 1551.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 2.787272757156329,
"min": 0.23863636803897945,
"max": 2.8200000217015093,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 153.30000164359808,
"min": 10.500000193715096,
"max": 155.100001193583,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06807530643518384,
"min": 0.06400337870404274,
"max": 0.07612948228112752,
"count": 118
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06807530643518384,
"min": 0.06400337870404274,
"max": 0.07612948228112752,
"count": 118
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.0016766203549159033,
"min": 0.0012503485261483795,
"max": 0.003760265681120086,
"count": 118
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.0016766203549159033,
"min": 0.0012503485261483795,
"max": 0.003760265681120086,
"count": 118
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0644992903999983e-06,
"min": 1.0644992903999983e-06,
"max": 0.00014873940084040002,
"count": 118
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0644992903999983e-06,
"min": 1.0644992903999983e-06,
"max": 0.00014873940084040002,
"count": 118
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10070960000000005,
"min": 0.10070960000000005,
"max": 0.19915960000000002,
"count": 118
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10070960000000005,
"min": 0.10070960000000005,
"max": 0.19915960000000002,
"count": 118
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.5409039999999954e-05,
"min": 4.5409039999999954e-05,
"max": 0.004958064040000001,
"count": 118
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.5409039999999954e-05,
"min": 4.5409039999999954e-05,
"max": 0.004958064040000001,
"count": 118
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1735587283",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735593713"
},
"total": 6430.14934202,
"count": 1,
"self": 1.1948224280013164,
"children": {
"run_training.setup": {
"total": 0.11315851000017574,
"count": 1,
"self": 0.11315851000017574
},
"TrainerController.start_learning": {
"total": 6428.841361081999,
"count": 1,
"self": 8.99585830144406,
"children": {
"TrainerController._reset_env": {
"total": 3.3011489050004457,
"count": 1,
"self": 3.3011489050004457
},
"TrainerController.advance": {
"total": 6416.401148671554,
"count": 181872,
"self": 4.145781111599717,
"children": {
"env_step": {
"total": 6412.255367559955,
"count": 181872,
"self": 5112.956623629537,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1295.060977182069,
"count": 181872,
"self": 24.128962340185353,
"children": {
"TorchPolicy.evaluate": {
"total": 1270.9320148418838,
"count": 181872,
"self": 1270.9320148418838
}
}
},
"workers": {
"total": 4.237766748348804,
"count": 181872,
"self": 0.0,
"children": {
"worker_root": {
"total": 6409.453978358057,
"count": 181872,
"is_parallel": true,
"self": 3285.7820006785623,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005012800999793399,
"count": 1,
"is_parallel": true,
"self": 0.00137477699900046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0036380240007929388,
"count": 10,
"is_parallel": true,
"self": 0.0036380240007929388
}
}
},
"UnityEnvironment.step": {
"total": 0.04326236700035224,
"count": 1,
"is_parallel": true,
"self": 0.0008554580008421908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004659260002881638,
"count": 1,
"is_parallel": true,
"self": 0.0004659260002881638
},
"communicator.exchange": {
"total": 0.03892191699924297,
"count": 1,
"is_parallel": true,
"self": 0.03892191699924297
},
"steps_from_proto": {
"total": 0.0030190659999789204,
"count": 1,
"is_parallel": true,
"self": 0.00048076099938043626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002538305000598484,
"count": 10,
"is_parallel": true,
"self": 0.002538305000598484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3123.6719776794944,
"count": 181871,
"is_parallel": true,
"self": 150.9198243530318,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.59267247502885,
"count": 181871,
"is_parallel": true,
"self": 76.59267247502885
},
"communicator.exchange": {
"total": 2449.197534630912,
"count": 181871,
"is_parallel": true,
"self": 2449.197534630912
},
"steps_from_proto": {
"total": 446.9619462205219,
"count": 181871,
"is_parallel": true,
"self": 87.61080271079481,
"children": {
"_process_rank_one_or_two_observation": {
"total": 359.3511435097271,
"count": 1818710,
"is_parallel": true,
"self": 359.3511435097271
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0005380050006351667,
"count": 1,
"self": 0.0005380050006351667,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 6309.161478470472,
"count": 11826943,
"is_parallel": true,
"self": 274.49397868472533,
"children": {
"process_trajectory": {
"total": 4280.637665592756,
"count": 11826943,
"is_parallel": true,
"self": 4273.37227616075,
"children": {
"RLTrainer._checkpoint": {
"total": 7.2653894320064865,
"count": 40,
"is_parallel": true,
"self": 7.2653894320064865
}
}
},
"_update_policy": {
"total": 1754.0298341929902,
"count": 118,
"is_parallel": true,
"self": 640.3592346847399,
"children": {
"TorchPPOOptimizer.update": {
"total": 1113.6705995082502,
"count": 46491,
"is_parallel": true,
"self": 1113.6705995082502
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14266719899933378,
"count": 1,
"self": 0.001825680998081225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14084151800125255,
"count": 1,
"self": 0.14084151800125255
}
}
}
}
}
}
}