vineetsharma's picture
First Push
7383227
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9224250316619873,
"min": 0.9224250316619873,
"max": 2.861732006072998,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8817.4609375,
"min": 8817.4609375,
"max": 29495.87109375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.70018482208252,
"min": 0.4953230917453766,
"max": 12.70018482208252,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2476.5361328125,
"min": 96.09268188476562,
"max": 2521.640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06168667495013306,
"min": 0.06168667495013306,
"max": 0.07325716725180803,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24674669980053224,
"min": 0.24674669980053224,
"max": 0.3553522129454102,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1883247481914712,
"min": 0.10059189743718461,
"max": 0.27830009197487554,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7532989927658847,
"min": 0.40236758974873843,
"max": 1.3915004598743776,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.136363636363637,
"min": 3.159090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 139.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.159090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 139.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689958233",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "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": "1689958696"
},
"total": 463.2378089719999,
"count": 1,
"self": 0.43611064599986094,
"children": {
"run_training.setup": {
"total": 0.051667130000055295,
"count": 1,
"self": 0.051667130000055295
},
"TrainerController.start_learning": {
"total": 462.750031196,
"count": 1,
"self": 0.5237024999962614,
"children": {
"TrainerController._reset_env": {
"total": 5.863468773000022,
"count": 1,
"self": 5.863468773000022
},
"TrainerController.advance": {
"total": 456.2233452400037,
"count": 18202,
"self": 0.24401692100491346,
"children": {
"env_step": {
"total": 455.9793283189988,
"count": 18202,
"self": 333.8093931580089,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.90380469099682,
"count": 18202,
"self": 1.7298239119853633,
"children": {
"TorchPolicy.evaluate": {
"total": 120.17398077901146,
"count": 18202,
"self": 120.17398077901146
}
}
},
"workers": {
"total": 0.26613046999307244,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 461.4339967659961,
"count": 18202,
"is_parallel": true,
"self": 222.57320252400257,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006824661999985437,
"count": 1,
"is_parallel": true,
"self": 0.004568842999560729,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002255819000424708,
"count": 10,
"is_parallel": true,
"self": 0.002255819000424708
}
}
},
"UnityEnvironment.step": {
"total": 0.03735806200006664,
"count": 1,
"is_parallel": true,
"self": 0.000603243000114162,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002724400000033711,
"count": 1,
"is_parallel": true,
"self": 0.0002724400000033711
},
"communicator.exchange": {
"total": 0.03439678699999149,
"count": 1,
"is_parallel": true,
"self": 0.03439678699999149
},
"steps_from_proto": {
"total": 0.0020855919999576145,
"count": 1,
"is_parallel": true,
"self": 0.00038325400021221867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017023379997453958,
"count": 10,
"is_parallel": true,
"self": 0.0017023379997453958
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.86079424199352,
"count": 18201,
"is_parallel": true,
"self": 10.31367461500713,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.087626347001105,
"count": 18201,
"is_parallel": true,
"self": 5.087626347001105
},
"communicator.exchange": {
"total": 189.62229734597815,
"count": 18201,
"is_parallel": true,
"self": 189.62229734597815
},
"steps_from_proto": {
"total": 33.83719593400713,
"count": 18201,
"is_parallel": true,
"self": 6.205965364108579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.63123056989855,
"count": 182010,
"is_parallel": true,
"self": 27.63123056989855
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015372100006061373,
"count": 1,
"self": 0.00015372100006061373,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.6228161239833,
"count": 418973,
"is_parallel": true,
"self": 9.424474013911095,
"children": {
"process_trajectory": {
"total": 244.05422068707264,
"count": 418973,
"is_parallel": true,
"self": 243.0424903720725,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0117303150001362,
"count": 4,
"is_parallel": true,
"self": 1.0117303150001362
}
}
},
"_update_policy": {
"total": 199.14412142299955,
"count": 90,
"is_parallel": true,
"self": 80.99569623900345,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.1484251839961,
"count": 4584,
"is_parallel": true,
"self": 118.1484251839961
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13936096199995518,
"count": 1,
"self": 0.0008748669999931735,
"children": {
"RLTrainer._checkpoint": {
"total": 0.138486094999962,
"count": 1,
"self": 0.138486094999962
}
}
}
}
}
}
}