ppo-Pyramids / run_logs /timers.json
mdapri's picture
copied almost entirey
45e74f2
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1424291580915451,
"min": 0.13603121042251587,
"max": 1.4563888311386108,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4229.576171875,
"min": 4080.5712890625,
"max": 44181.01171875,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999933.0,
"min": 29952.0,
"max": 2999933.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999933.0,
"min": 29952.0,
"max": 2999933.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7449614405632019,
"min": -0.17585518956184387,
"max": 0.851775586605072,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 214.54888916015625,
"min": -41.67768096923828,
"max": 256.38446044921875,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.010200072079896927,
"min": -0.02408018335700035,
"max": 0.36306333541870117,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -2.9376206398010254,
"min": -6.886932373046875,
"max": 86.04601287841797,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06822247157595317,
"min": 0.06354586928794279,
"max": 0.0755908833393949,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9551146020633443,
"min": 0.4570556149908994,
"max": 1.0582723667515286,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01480097603705041,
"min": 0.00011329088487269664,
"max": 0.017498435352449417,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20721366451870574,
"min": 0.0015785147689869445,
"max": 0.25212832103773275,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.3996781049023841e-06,
"min": 1.3996781049023841e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.959549346863338e-05,
"min": 1.959549346863338e-05,
"max": 0.003716870361043267,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1004665261904762,
"min": 0.1004665261904762,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4065313666666668,
"min": 1.3897045333333333,
"max": 2.7225089000000002,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.6605966428571546e-05,
"min": 5.6605966428571546e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0007924835300000016,
"min": 0.0007924835300000016,
"max": 0.12391177766,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.004884503781795502,
"min": 0.004550025798380375,
"max": 0.41251513361930847,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.06838305294513702,
"min": 0.0637003630399704,
"max": 2.887605905532837,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 241.50420168067228,
"min": 222.0,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28739.0,
"min": 15984.0,
"max": 32834.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7536833134790262,
"min": -1.0000000521540642,
"max": 1.7640879878997802,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 210.44199761748314,
"min": -32.000001668930054,
"max": 239.1353993266821,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7536833134790262,
"min": -1.0000000521540642,
"max": 1.7640879878997802,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 210.44199761748314,
"min": -32.000001668930054,
"max": 239.1353993266821,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.012695291051841195,
"min": 0.01118000469546132,
"max": 8.320174556225538,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.5234349262209435,
"min": 1.3379464278987143,
"max": 133.1227928996086,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677432278",
"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=PyramidsTraining --no-graphics --force",
"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": "1.22.4",
"end_time_seconds": "1677439557"
},
"total": 7278.420029442001,
"count": 1,
"self": 0.5449051720006537,
"children": {
"run_training.setup": {
"total": 0.12886468799999307,
"count": 1,
"self": 0.12886468799999307
},
"TrainerController.start_learning": {
"total": 7277.746259582,
"count": 1,
"self": 3.9357067097253093,
"children": {
"TrainerController._reset_env": {
"total": 9.791485017000014,
"count": 1,
"self": 9.791485017000014
},
"TrainerController.advance": {
"total": 7263.928225144275,
"count": 194459,
"self": 4.17071447908711,
"children": {
"env_step": {
"total": 5023.268950977117,
"count": 194459,
"self": 4693.198812675754,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.6351342752412,
"count": 194459,
"self": 14.079667260238011,
"children": {
"TorchPolicy.evaluate": {
"total": 313.5554670150032,
"count": 187545,
"self": 107.01761920904042,
"children": {
"TorchPolicy.sample_actions": {
"total": 206.5378478059628,
"count": 187545,
"self": 206.5378478059628
}
}
}
}
},
"workers": {
"total": 2.4350040261218737,
"count": 194459,
"self": 0.0,
"children": {
"worker_root": {
"total": 7263.429101604857,
"count": 194459,
"is_parallel": true,
"self": 2914.6889630238493,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005110538999986147,
"count": 1,
"is_parallel": true,
"self": 0.003858430999940765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012521080000453821,
"count": 8,
"is_parallel": true,
"self": 0.0012521080000453821
}
}
},
"UnityEnvironment.step": {
"total": 0.04849622200001136,
"count": 1,
"is_parallel": true,
"self": 0.0005404970000313369,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005035579999912443,
"count": 1,
"is_parallel": true,
"self": 0.0005035579999912443
},
"communicator.exchange": {
"total": 0.04580672000000163,
"count": 1,
"is_parallel": true,
"self": 0.04580672000000163
},
"steps_from_proto": {
"total": 0.0016454469999871435,
"count": 1,
"is_parallel": true,
"self": 0.0004646010000328715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001180845999954272,
"count": 8,
"is_parallel": true,
"self": 0.001180845999954272
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4348.740138581008,
"count": 194458,
"is_parallel": true,
"self": 95.3288179987976,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 68.23474337004328,
"count": 194458,
"is_parallel": true,
"self": 68.23474337004328
},
"communicator.exchange": {
"total": 3909.9703435321317,
"count": 194458,
"is_parallel": true,
"self": 3909.9703435321317
},
"steps_from_proto": {
"total": 275.20623368003567,
"count": 194458,
"is_parallel": true,
"self": 64.9056568987832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 210.30057678125246,
"count": 1555664,
"is_parallel": true,
"self": 210.30057678125246
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2236.4885596880704,
"count": 194459,
"self": 7.861621855073281,
"children": {
"process_trajectory": {
"total": 495.71402585700866,
"count": 194459,
"self": 495.117502337009,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5965235199996641,
"count": 6,
"self": 0.5965235199996641
}
}
},
"_update_policy": {
"total": 1732.9129119759887,
"count": 1386,
"self": 671.303681670865,
"children": {
"TorchPPOOptimizer.update": {
"total": 1061.6092303051237,
"count": 68493,
"self": 1061.6092303051237
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.980006557772867e-07,
"count": 1,
"self": 7.980006557772867e-07
},
"TrainerController._save_models": {
"total": 0.09084191299916711,
"count": 1,
"self": 0.0014416439989872742,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08940026900017983,
"count": 1,
"self": 0.08940026900017983
}
}
}
}
}
}
}