rgny's picture
First Push
f970283
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7052878141403198,
"min": 0.6651203632354736,
"max": 1.423171877861023,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 20853.94921875,
"min": 20049.388671875,
"max": 43173.34375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989914.0,
"min": 29952.0,
"max": 989914.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989914.0,
"min": 29952.0,
"max": 989914.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.0724949911236763,
"min": -0.10466817766427994,
"max": 0.07837730646133423,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 17.90626335144043,
"min": -25.120363235473633,
"max": 18.575422286987305,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02033374272286892,
"min": 0.016492972150444984,
"max": 0.39002150297164917,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.022434234619141,
"min": 3.974806308746338,
"max": 93.31395721435547,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07275075971431631,
"min": 0.06487429027778664,
"max": 0.07275075971431631,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0185106360004283,
"min": 0.496429091672033,
"max": 1.0451105359859545,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.007518292994366978,
"min": 0.00043651184487839733,
"max": 0.010180770577512321,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.10525610192113768,
"min": 0.0061111658282975625,
"max": 0.10525610192113768,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.3634904026785755e-06,
"min": 7.3634904026785755e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010308886563750006,
"min": 0.00010308886563750006,
"max": 0.0035081636306122,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245446428571428,
"min": 0.10245446428571428,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343625,
"min": 1.3886848,
"max": 2.5693878000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002552009821428573,
"min": 0.0002552009821428573,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035728137500000024,
"min": 0.0035728137500000024,
"max": 0.11696184122,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.017344454303383827,
"min": 0.017344454303383827,
"max": 0.6104449033737183,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.24282234907150269,
"min": 0.24282234907150269,
"max": 4.273114204406738,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 814.7368421052631,
"min": 802.3846153846154,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30960.0,
"min": 15984.0,
"max": 32765.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.16283238679170609,
"min": -1.0000000521540642,
"max": 0.16283238679170609,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 6.024798311293125,
"min": -29.884001709520817,
"max": 6.024798311293125,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.16283238679170609,
"min": -1.0000000521540642,
"max": 0.16283238679170609,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 6.024798311293125,
"min": -29.884001709520817,
"max": 6.024798311293125,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.1445691216441274,
"min": 0.1445691216441274,
"max": 13.288411520421505,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.349057500832714,
"min": 5.349057500832714,
"max": 212.61458432674408,
"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": "1703682740",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703684955"
},
"total": 2214.7285601900003,
"count": 1,
"self": 0.49628057300014916,
"children": {
"run_training.setup": {
"total": 0.05177561400000741,
"count": 1,
"self": 0.05177561400000741
},
"TrainerController.start_learning": {
"total": 2214.180504003,
"count": 1,
"self": 1.469871410025462,
"children": {
"TrainerController._reset_env": {
"total": 3.230556774999968,
"count": 1,
"self": 3.230556774999968
},
"TrainerController.advance": {
"total": 2209.3876154789746,
"count": 63190,
"self": 1.5468917630259966,
"children": {
"env_step": {
"total": 1583.423337303964,
"count": 63190,
"self": 1444.1023496049377,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.4005725040235,
"count": 63190,
"self": 4.99130222301153,
"children": {
"TorchPolicy.evaluate": {
"total": 133.40927028101197,
"count": 62559,
"self": 133.40927028101197
}
}
},
"workers": {
"total": 0.9204151950028745,
"count": 63190,
"self": 0.0,
"children": {
"worker_root": {
"total": 2208.934247378078,
"count": 63190,
"is_parallel": true,
"self": 891.1650272720685,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004667310999991514,
"count": 1,
"is_parallel": true,
"self": 0.0033131619998698625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013541490001216516,
"count": 8,
"is_parallel": true,
"self": 0.0013541490001216516
}
}
},
"UnityEnvironment.step": {
"total": 0.05756726999999273,
"count": 1,
"is_parallel": true,
"self": 0.0006284350000100858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005096670000170889,
"count": 1,
"is_parallel": true,
"self": 0.0005096670000170889
},
"communicator.exchange": {
"total": 0.054681197999968845,
"count": 1,
"is_parallel": true,
"self": 0.054681197999968845
},
"steps_from_proto": {
"total": 0.0017479699999967124,
"count": 1,
"is_parallel": true,
"self": 0.0003653930000382388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013825769999584736,
"count": 8,
"is_parallel": true,
"self": 0.0013825769999584736
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.7692201060095,
"count": 63189,
"is_parallel": true,
"self": 36.81734420698399,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.280523381995295,
"count": 63189,
"is_parallel": true,
"self": 26.280523381995295
},
"communicator.exchange": {
"total": 1147.9923972800175,
"count": 63189,
"is_parallel": true,
"self": 1147.9923972800175
},
"steps_from_proto": {
"total": 106.67895523701264,
"count": 63189,
"is_parallel": true,
"self": 21.93461185103962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.74434338597302,
"count": 505512,
"is_parallel": true,
"self": 84.74434338597302
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.4173864119847,
"count": 63190,
"self": 2.9123688830192123,
"children": {
"process_trajectory": {
"total": 127.30548172896772,
"count": 63190,
"self": 127.09104887596789,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21443285299983472,
"count": 2,
"self": 0.21443285299983472
}
}
},
"_update_policy": {
"total": 494.19953579999776,
"count": 447,
"self": 291.5421684159925,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.65736738400528,
"count": 22851,
"self": 202.65736738400528
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1059996722906362e-06,
"count": 1,
"self": 1.1059996722906362e-06
},
"TrainerController._save_models": {
"total": 0.09245923300022696,
"count": 1,
"self": 0.0014787270006308972,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09098050599959606,
"count": 1,
"self": 0.09098050599959606
}
}
}
}
}
}
}