ppo-Pyramids / run_logs /timers.json
kostasang's picture
First push
42588ac
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4791682958602905,
"min": 0.4791682958602905,
"max": 1.4421725273132324,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14398.048828125,
"min": 14398.048828125,
"max": 43749.74609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989961.0,
"min": 29952.0,
"max": 989961.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989961.0,
"min": 29952.0,
"max": 989961.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.49033644795417786,
"min": -0.09734136611223221,
"max": 0.49033644795417786,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 132.8811798095703,
"min": -23.361927032470703,
"max": 132.8811798095703,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.041619885712862015,
"min": -0.021851157769560814,
"max": 0.3997831344604492,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 11.2789888381958,
"min": -5.790556907653809,
"max": 94.74860382080078,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06585533685179386,
"min": 0.06500913550467778,
"max": 0.07441256111358395,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.921974715925114,
"min": 0.48111711419053677,
"max": 1.1161884167037592,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017638900902059322,
"min": 0.0007462163176597132,
"max": 0.018065774854039773,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24694461262883052,
"min": 0.009700812129576271,
"max": 0.2709866228105966,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.513211781342856e-06,
"min": 7.513211781342856e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010518496493879998,
"min": 0.00010518496493879998,
"max": 0.0033798728733758,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250437142857141,
"min": 0.10250437142857141,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4350611999999998,
"min": 1.3886848,
"max": 2.5266242,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002601867057142857,
"min": 0.0002601867057142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036426138800000002,
"min": 0.0036426138800000002,
"max": 0.11268975758000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010730870999395847,
"min": 0.010710031725466251,
"max": 0.42130962014198303,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.150232195854187,
"min": 0.14994044601917267,
"max": 2.949167251586914,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 379.3,
"min": 347.9764705882353,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30344.0,
"min": 15984.0,
"max": 33214.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4963265609326242,
"min": -1.0000000521540642,
"max": 1.5578776216682266,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 118.20979831367731,
"min": -29.665801607072353,
"max": 132.41959784179926,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4963265609326242,
"min": -1.0000000521540642,
"max": 1.5578776216682266,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 118.20979831367731,
"min": -29.665801607072353,
"max": 132.41959784179926,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0419787859847722,
"min": 0.04178487084675854,
"max": 8.16828243713826,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3163240927970037,
"min": 3.2996673882880714,
"max": 130.69251899421215,
"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": "1674553898",
"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": "1674555856"
},
"total": 1957.322265406,
"count": 1,
"self": 0.4236693729997114,
"children": {
"run_training.setup": {
"total": 0.10783148600012282,
"count": 1,
"self": 0.10783148600012282
},
"TrainerController.start_learning": {
"total": 1956.7907645470002,
"count": 1,
"self": 1.2794792359434268,
"children": {
"TrainerController._reset_env": {
"total": 6.043762947999994,
"count": 1,
"self": 6.043762947999994
},
"TrainerController.advance": {
"total": 1949.3839524250568,
"count": 63634,
"self": 1.2661638040676735,
"children": {
"env_step": {
"total": 1306.8255035320262,
"count": 63634,
"self": 1201.4417183771354,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.58157601694415,
"count": 63634,
"self": 4.216983473994333,
"children": {
"TorchPolicy.evaluate": {
"total": 100.36459254294982,
"count": 62566,
"self": 33.253090491000876,
"children": {
"TorchPolicy.sample_actions": {
"total": 67.11150205194895,
"count": 62566,
"self": 67.11150205194895
}
}
}
}
},
"workers": {
"total": 0.8022091379466474,
"count": 63634,
"self": 0.0,
"children": {
"worker_root": {
"total": 1952.2821370390402,
"count": 63634,
"is_parallel": true,
"self": 848.4193750889542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016610479999599193,
"count": 1,
"is_parallel": true,
"self": 0.000581341999804863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010797060001550562,
"count": 8,
"is_parallel": true,
"self": 0.0010797060001550562
}
}
},
"UnityEnvironment.step": {
"total": 0.06352531900006397,
"count": 1,
"is_parallel": true,
"self": 0.0004829060001156904,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000406127999895034,
"count": 1,
"is_parallel": true,
"self": 0.000406127999895034
},
"communicator.exchange": {
"total": 0.06109517300001244,
"count": 1,
"is_parallel": true,
"self": 0.06109517300001244
},
"steps_from_proto": {
"total": 0.0015411120000408118,
"count": 1,
"is_parallel": true,
"self": 0.0004082860000380606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011328260000027512,
"count": 8,
"is_parallel": true,
"self": 0.0011328260000027512
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1103.862761950086,
"count": 63633,
"is_parallel": true,
"self": 27.27663407312525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.548857784943266,
"count": 63633,
"is_parallel": true,
"self": 21.548857784943266
},
"communicator.exchange": {
"total": 958.1758094469849,
"count": 63633,
"is_parallel": true,
"self": 958.1758094469849
},
"steps_from_proto": {
"total": 96.8614606450326,
"count": 63633,
"is_parallel": true,
"self": 21.45196464977994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.40949599525266,
"count": 509064,
"is_parallel": true,
"self": 75.40949599525266
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 641.2922850889629,
"count": 63634,
"self": 2.5487159248975786,
"children": {
"process_trajectory": {
"total": 141.36624488906637,
"count": 63634,
"self": 141.1757143230666,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19053056599977936,
"count": 2,
"self": 0.19053056599977936
}
}
},
"_update_policy": {
"total": 497.37732427499895,
"count": 454,
"self": 187.2217190429849,
"children": {
"TorchPPOOptimizer.update": {
"total": 310.15560523201407,
"count": 22782,
"self": 310.15560523201407
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.149998732027598e-07,
"count": 1,
"self": 9.149998732027598e-07
},
"TrainerController._save_models": {
"total": 0.08356902300010915,
"count": 1,
"self": 0.00131671900044239,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08225230399966676,
"count": 1,
"self": 0.08225230399966676
}
}
}
}
}
}
}