dimitarrskv's picture
First Push
9876be7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.2363524436950684,
"min": 2.2363524436950684,
"max": 2.8672332763671875,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 22558.0859375,
"min": 22558.0859375,
"max": 29426.416015625,
"count": 5
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.2450300455093384,
"min": 0.23361347615718842,
"max": 1.2450300455093384,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 241.53582763671875,
"min": 45.321014404296875,
"max": 241.53582763671875,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06124697149768026,
"min": 0.06124697149768026,
"max": 0.07294259015773194,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24498788599072105,
"min": 0.24498788599072105,
"max": 0.36471295078865973,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1434110276327998,
"min": 0.06831031600435666,
"max": 0.15425068180935056,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5736441105311992,
"min": 0.27324126401742665,
"max": 0.7712534090467528,
"count": 5
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.9928090024000003e-05,
"min": 2.9928090024000003e-05,
"max": 0.00026752801082399996,
"count": 5
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00011971236009600001,
"min": 0.00011971236009600001,
"max": 0.0010701120432959998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10997600000000002,
"min": 0.10997600000000002,
"max": 0.18917599999999998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4399040000000001,
"min": 0.4399040000000001,
"max": 0.8468800000000001,
"count": 5
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0005078024,
"min": 0.0005078024,
"max": 0.0044598824,
"count": 5
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0020312096,
"min": 0.0020312096,
"max": 0.0178395296,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 13.204545454545455,
"min": 3.477272727272727,
"max": 13.204545454545455,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 581.0,
"min": 153.0,
"max": 620.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 13.204545454545455,
"min": 3.477272727272727,
"max": 13.204545454545455,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 581.0,
"min": 153.0,
"max": 620.0,
"count": 5
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1692909474",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=SnowballTarget3 --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": "1692909599"
},
"total": 125.17964185099936,
"count": 1,
"self": 0.4391010389999792,
"children": {
"run_training.setup": {
"total": 0.0575537759996223,
"count": 1,
"self": 0.0575537759996223
},
"TrainerController.start_learning": {
"total": 124.68298703599976,
"count": 1,
"self": 0.24290085699794872,
"children": {
"TrainerController._reset_env": {
"total": 1.3952593630001502,
"count": 1,
"self": 1.3952593630001502
},
"TrainerController.advance": {
"total": 122.9464875040012,
"count": 4600,
"self": 0.09349419199406839,
"children": {
"env_step": {
"total": 122.85299331200713,
"count": 4600,
"self": 98.89929144103644,
"children": {
"SubprocessEnvManager._take_step": {
"total": 23.768609807979374,
"count": 4600,
"self": 0.6867739279950911,
"children": {
"TorchPolicy.evaluate": {
"total": 23.081835879984283,
"count": 4600,
"self": 23.081835879984283
}
}
},
"workers": {
"total": 0.1850920629913162,
"count": 4600,
"self": 0.0,
"children": {
"worker_root": {
"total": 124.11924013100906,
"count": 4600,
"is_parallel": true,
"self": 56.94668957199701,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023171600005298387,
"count": 1,
"is_parallel": true,
"self": 0.0005395800008045626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017775799997252761,
"count": 10,
"is_parallel": true,
"self": 0.0017775799997252761
}
}
},
"UnityEnvironment.step": {
"total": 0.10602262199972756,
"count": 1,
"is_parallel": true,
"self": 0.0004947389988956274,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044537000030686613,
"count": 1,
"is_parallel": true,
"self": 0.00044537000030686613
},
"communicator.exchange": {
"total": 0.10330869300014456,
"count": 1,
"is_parallel": true,
"self": 0.10330869300014456
},
"steps_from_proto": {
"total": 0.0017738200003805105,
"count": 1,
"is_parallel": true,
"self": 0.0005362400024750968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012375799979054136,
"count": 10,
"is_parallel": true,
"self": 0.0012375799979054136
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 67.17255055901205,
"count": 4599,
"is_parallel": true,
"self": 2.624299993030945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.643167735984207,
"count": 4599,
"is_parallel": true,
"self": 1.643167735984207
},
"communicator.exchange": {
"total": 54.33815692600547,
"count": 4599,
"is_parallel": true,
"self": 54.33815692600547
},
"steps_from_proto": {
"total": 8.566925903991432,
"count": 4599,
"is_parallel": true,
"self": 1.7302336729280796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.836692231063353,
"count": 45990,
"is_parallel": true,
"self": 6.836692231063353
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0004941500001223176,
"count": 1,
"self": 0.0004941500001223176,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 121.96505981092105,
"count": 140467,
"is_parallel": true,
"self": 2.8372555947498768,
"children": {
"process_trajectory": {
"total": 67.13759573317111,
"count": 140467,
"is_parallel": true,
"self": 66.93132985817101,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20626587500009919,
"count": 1,
"is_parallel": true,
"self": 0.20626587500009919
}
}
},
"_update_policy": {
"total": 51.99020848300006,
"count": 22,
"is_parallel": true,
"self": 14.441091913013224,
"children": {
"TorchPPOOptimizer.update": {
"total": 37.549116569986836,
"count": 1119,
"is_parallel": true,
"self": 37.549116569986836
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09784516200033977,
"count": 1,
"self": 0.0007796990003043902,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09706546300003538,
"count": 1,
"self": 0.09706546300003538
}
}
}
}
}
}
}