Hanna Tochylina
First Push
6bdfc1f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5282027125358582,
"min": 0.48361876606941223,
"max": 1.492153286933899,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15972.849609375,
"min": 14477.611328125,
"max": 45265.9609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989990.0,
"min": 29952.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989990.0,
"min": 29952.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6084794998168945,
"min": -0.10755988210439682,
"max": 0.6084794998168945,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 170.374267578125,
"min": -25.921932220458984,
"max": 170.374267578125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.37467464804649353,
"min": -0.37467464804649353,
"max": 0.45292383432388306,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -104.90889739990234,
"min": -104.90889739990234,
"max": 107.34294891357422,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07109848594215387,
"min": 0.06532655008101658,
"max": 0.07280064633216236,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9953788031901543,
"min": 0.47199862423699473,
"max": 1.0856040355272354,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.028854208975514797,
"min": 0.0007377053292587549,
"max": 0.028854208975514797,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.40395892565720715,
"min": 0.008114758621846303,
"max": 0.40395892565720715,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.430090380478573e-06,
"min": 7.430090380478573e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010402126532670002,
"min": 0.00010402126532670002,
"max": 0.0032541431152857,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1024766642857143,
"min": 0.1024766642857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4346733,
"min": 1.3691136000000002,
"max": 2.4440867000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025741876214285727,
"min": 0.00025741876214285727,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036038626700000014,
"min": 0.0036038626700000014,
"max": 0.10849295857,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.016299067065119743,
"min": 0.016299067065119743,
"max": 0.5785345435142517,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2281869351863861,
"min": 0.2281869351863861,
"max": 4.049741744995117,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 316.81188118811883,
"min": 316.81188118811883,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31998.0,
"min": 15984.0,
"max": 32740.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.643570283704465,
"min": -1.0000000521540642,
"max": 1.643570283704465,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 166.00059865415096,
"min": -32.000001668930054,
"max": 166.00059865415096,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.643570283704465,
"min": -1.0000000521540642,
"max": 1.643570283704465,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 166.00059865415096,
"min": -32.000001668930054,
"max": 166.00059865415096,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05309938759189145,
"min": 0.05309938759189145,
"max": 12.505519585683942,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.363038146781037,
"min": 4.832071086624637,
"max": 200.08831337094307,
"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": "1680612553",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 Training1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.10.1+cu111",
"numpy_version": "1.21.2",
"end_time_seconds": "1680615227"
},
"total": 2674.115453071,
"count": 1,
"self": 0.48752148999983547,
"children": {
"run_training.setup": {
"total": 0.04115373100012221,
"count": 1,
"self": 0.04115373100012221
},
"TrainerController.start_learning": {
"total": 2673.58677785,
"count": 1,
"self": 2.1634818859938605,
"children": {
"TrainerController._reset_env": {
"total": 8.300323212999956,
"count": 1,
"self": 8.300323212999956
},
"TrainerController.advance": {
"total": 2663.0271512760064,
"count": 63589,
"self": 2.3906694889842584,
"children": {
"env_step": {
"total": 1900.7699802551092,
"count": 63589,
"self": 1735.9386623580108,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.54156498607426,
"count": 63589,
"self": 6.1455436331339115,
"children": {
"TorchPolicy.evaluate": {
"total": 157.39602135294035,
"count": 62556,
"self": 157.39602135294035
}
}
},
"workers": {
"total": 1.2897529110241521,
"count": 63589,
"self": 0.0,
"children": {
"worker_root": {
"total": 2665.9235682398407,
"count": 63589,
"is_parallel": true,
"self": 1090.3892215568658,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026992540001629095,
"count": 1,
"is_parallel": true,
"self": 0.0011655580001388444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015336960000240651,
"count": 8,
"is_parallel": true,
"self": 0.0015336960000240651
}
}
},
"UnityEnvironment.step": {
"total": 0.08376591100022779,
"count": 1,
"is_parallel": true,
"self": 0.0005762099999628845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005720600001950515,
"count": 1,
"is_parallel": true,
"self": 0.0005720600001950515
},
"communicator.exchange": {
"total": 0.08089719600002354,
"count": 1,
"is_parallel": true,
"self": 0.08089719600002354
},
"steps_from_proto": {
"total": 0.0017204450000463112,
"count": 1,
"is_parallel": true,
"self": 0.0003923290005332092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001328115999513102,
"count": 8,
"is_parallel": true,
"self": 0.001328115999513102
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1575.534346682975,
"count": 63588,
"is_parallel": true,
"self": 37.03743486211124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.039922542833665,
"count": 63588,
"is_parallel": true,
"self": 27.039922542833665
},
"communicator.exchange": {
"total": 1396.7944516441003,
"count": 63588,
"is_parallel": true,
"self": 1396.7944516441003
},
"steps_from_proto": {
"total": 114.66253763392979,
"count": 63588,
"is_parallel": true,
"self": 26.45896981207443,
"children": {
"_process_rank_one_or_two_observation": {
"total": 88.20356782185536,
"count": 508704,
"is_parallel": true,
"self": 88.20356782185536
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 759.866501531913,
"count": 63589,
"self": 4.09566039491574,
"children": {
"process_trajectory": {
"total": 151.59249304801278,
"count": 63589,
"self": 151.387095366013,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20539768199978425,
"count": 2,
"self": 0.20539768199978425
}
}
},
"_update_policy": {
"total": 604.1783480889844,
"count": 444,
"self": 363.99870690595435,
"children": {
"TorchPPOOptimizer.update": {
"total": 240.17964118303007,
"count": 22836,
"self": 240.17964118303007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1279998943791725e-06,
"count": 1,
"self": 1.1279998943791725e-06
},
"TrainerController._save_models": {
"total": 0.09582034699997166,
"count": 1,
"self": 0.0014546880001944373,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09436565899977722,
"count": 1,
"self": 0.09436565899977722
}
}
}
}
}
}
}