ppo-PyramidsRND / run_logs /timers.json
NathanaelM's picture
PyramidsRND initial training
d5fde43
raw
history blame
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.31749632954597473,
"min": 0.31628549098968506,
"max": 1.434346318244934,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9504.5703125,
"min": 9504.5703125,
"max": 43512.328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989878.0,
"min": 29952.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989878.0,
"min": 29952.0,
"max": 989878.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6455972194671631,
"min": -0.1168774738907814,
"max": 0.6455972194671631,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 182.70401000976562,
"min": -28.050594329833984,
"max": 182.70401000976562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0038588286843150854,
"min": -0.012985886074602604,
"max": 0.342542827129364,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1.0920485258102417,
"min": -3.467231512069702,
"max": 81.18264770507812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06685160312783502,
"min": 0.06489947712954457,
"max": 0.07449346778291922,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9359224437896901,
"min": 0.5214542744804346,
"max": 1.0712448345193657,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01624618123269331,
"min": 0.0007064353986446451,
"max": 0.01673300117124907,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22744653725770633,
"min": 0.008477224783735741,
"max": 0.25099501756873605,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.381340396728573e-06,
"min": 7.381340396728573e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010333876555420002,
"min": 0.00010333876555420002,
"max": 0.0032595956134681995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10246041428571429,
"min": 0.10246041428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4344458,
"min": 1.3886848,
"max": 2.4430154999999996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002557953871428572,
"min": 0.0002557953871428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035811354200000005,
"min": 0.0035811354200000005,
"max": 0.10867452681999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014713412150740623,
"min": 0.014713412150740623,
"max": 0.4901486933231354,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20598776638507843,
"min": 0.20598776638507843,
"max": 3.4310407638549805,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 311.4845360824742,
"min": 298.2736842105263,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30214.0,
"min": 15984.0,
"max": 32564.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6678886438153453,
"min": -1.0000000521540642,
"max": 1.7008144079717165,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 161.7851984500885,
"min": -32.000001668930054,
"max": 171.49519822001457,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6678886438153453,
"min": -1.0000000521540642,
"max": 1.7008144079717165,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 161.7851984500885,
"min": -32.000001668930054,
"max": 171.49519822001457,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04730263440680724,
"min": 0.04710952983495142,
"max": 9.47126466408372,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.588355537460302,
"min": 4.475405334320385,
"max": 151.5402346253395,
"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": "1673528805",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673530772"
},
"total": 1966.3738996270004,
"count": 1,
"self": 0.49645739900006447,
"children": {
"run_training.setup": {
"total": 0.10579771199991228,
"count": 1,
"self": 0.10579771199991228
},
"TrainerController.start_learning": {
"total": 1965.7716445160004,
"count": 1,
"self": 1.0602195659812423,
"children": {
"TrainerController._reset_env": {
"total": 6.199408854000012,
"count": 1,
"self": 6.199408854000012
},
"TrainerController.advance": {
"total": 1958.4230408650187,
"count": 63998,
"self": 1.132667132023471,
"children": {
"env_step": {
"total": 1310.3801226359706,
"count": 63998,
"self": 1213.9086770880385,
"children": {
"SubprocessEnvManager._take_step": {
"total": 95.7857063379688,
"count": 63998,
"self": 3.9717181050377803,
"children": {
"TorchPolicy.evaluate": {
"total": 91.81398823293102,
"count": 62558,
"self": 31.29640524986371,
"children": {
"TorchPolicy.sample_actions": {
"total": 60.517582983067314,
"count": 62558,
"self": 60.517582983067314
}
}
}
}
},
"workers": {
"total": 0.6857392099632307,
"count": 63998,
"self": 0.0,
"children": {
"worker_root": {
"total": 1961.749911086988,
"count": 63998,
"is_parallel": true,
"self": 837.9497522929596,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016201389998968807,
"count": 1,
"is_parallel": true,
"self": 0.0005881719994249579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010319670004719228,
"count": 8,
"is_parallel": true,
"self": 0.0010319670004719228
}
}
},
"UnityEnvironment.step": {
"total": 0.04600281200009704,
"count": 1,
"is_parallel": true,
"self": 0.00046246700003393926,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041897900018739165,
"count": 1,
"is_parallel": true,
"self": 0.00041897900018739165
},
"communicator.exchange": {
"total": 0.043566015000124025,
"count": 1,
"is_parallel": true,
"self": 0.043566015000124025
},
"steps_from_proto": {
"total": 0.0015553509997516812,
"count": 1,
"is_parallel": true,
"self": 0.0003953139994337107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011600370003179705,
"count": 8,
"is_parallel": true,
"self": 0.0011600370003179705
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1123.8001587940284,
"count": 63997,
"is_parallel": true,
"self": 26.777156282080796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.308974685993235,
"count": 63997,
"is_parallel": true,
"self": 21.308974685993235
},
"communicator.exchange": {
"total": 979.8572306959586,
"count": 63997,
"is_parallel": true,
"self": 979.8572306959586
},
"steps_from_proto": {
"total": 95.85679712999581,
"count": 63997,
"is_parallel": true,
"self": 20.548404130039216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.3083929999566,
"count": 511976,
"is_parallel": true,
"self": 75.3083929999566
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 646.9102510970247,
"count": 63998,
"self": 1.9911681770117866,
"children": {
"process_trajectory": {
"total": 140.85580570400953,
"count": 63998,
"self": 140.67063031000998,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1851753939995433,
"count": 2,
"self": 0.1851753939995433
}
}
},
"_update_policy": {
"total": 504.06327721600337,
"count": 445,
"self": 194.87653440804206,
"children": {
"TorchPPOOptimizer.update": {
"total": 309.1867428079613,
"count": 22827,
"self": 309.1867428079613
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.180004442692734e-07,
"count": 1,
"self": 8.180004442692734e-07
},
"TrainerController._save_models": {
"total": 0.0889744129999599,
"count": 1,
"self": 0.0014549489997079945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0875194640002519,
"count": 1,
"self": 0.0875194640002519
}
}
}
}
}
}
}