ppo-pyramids1 / run_logs /timers.json
Gabcsor's picture
First Push
2670293
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34369030594825745,
"min": 0.34369030594825745,
"max": 1.4309316873550415,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10360.2001953125,
"min": 10360.2001953125,
"max": 43408.7421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989998.0,
"min": 29881.0,
"max": 989998.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989998.0,
"min": 29881.0,
"max": 989998.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6210414171218872,
"min": -0.10244341194629669,
"max": 0.6853614449501038,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 177.6178436279297,
"min": -24.688861846923828,
"max": 198.75482177734375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030700059607625008,
"min": -0.043159276247024536,
"max": 0.5977907180786133,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.780217170715332,
"min": -11.048774719238281,
"max": 141.67640686035156,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06939903252683519,
"min": 0.06233179635121455,
"max": 0.0720544700055166,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0409854879025278,
"min": 0.547031991657553,
"max": 1.0520841325165284,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01547874139391306,
"min": 0.0010686538772508238,
"max": 0.0168100609052566,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2321811209086959,
"min": 0.012936508819425058,
"max": 0.2353408526735924,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.434997521700002e-06,
"min": 7.434997521700002e-06,
"max": 0.0002952145140951625,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011152496282550003,
"min": 0.00011152496282550003,
"max": 0.0035075051308316994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247830000000001,
"min": 0.10247830000000001,
"max": 0.1984048375,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5371745,
"min": 1.4778174,
"max": 2.5724283,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002575821700000001,
"min": 0.0002575821700000001,
"max": 0.00984064326625,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003863732550000001,
"min": 0.003863732550000001,
"max": 0.11693991316999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013414845801889896,
"min": 0.013414845801889896,
"max": 0.4765087366104126,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20122268795967102,
"min": 0.18816408514976501,
"max": 3.812069892883301,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 317.65346534653463,
"min": 281.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32083.0,
"min": 16808.0,
"max": 32727.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6229148308681969,
"min": -0.9999871489501768,
"max": 1.6932708170885842,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 163.9143979176879,
"min": -30.999601617455482,
"max": 177.72439797222614,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6229148308681969,
"min": -0.9999871489501768,
"max": 1.6932708170885842,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 163.9143979176879,
"min": -30.999601617455482,
"max": 177.72439797222614,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04384517049305095,
"min": 0.04041078597753464,
"max": 9.491265858797465,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.428362219798146,
"min": 4.186420904588886,
"max": 161.35151959955692,
"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": "1678218596",
"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": "1.22.4",
"end_time_seconds": "1678221085"
},
"total": 2489.905876179,
"count": 1,
"self": 0.4914703599997665,
"children": {
"run_training.setup": {
"total": 0.12412680300008105,
"count": 1,
"self": 0.12412680300008105
},
"TrainerController.start_learning": {
"total": 2489.290279016,
"count": 1,
"self": 1.6697771869721691,
"children": {
"TrainerController._reset_env": {
"total": 6.459935792999886,
"count": 1,
"self": 6.459935792999886
},
"TrainerController.advance": {
"total": 2481.0721834390283,
"count": 64079,
"self": 1.6785594619477706,
"children": {
"env_step": {
"total": 1706.2756524480133,
"count": 64079,
"self": 1580.5066431909738,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.76242160898983,
"count": 64079,
"self": 4.947523783990391,
"children": {
"TorchPolicy.evaluate": {
"total": 119.81489782499943,
"count": 62568,
"self": 40.610394208001935,
"children": {
"TorchPolicy.sample_actions": {
"total": 79.2045036169975,
"count": 62568,
"self": 79.2045036169975
}
}
}
}
},
"workers": {
"total": 1.0065876480496172,
"count": 64079,
"self": 0.0,
"children": {
"worker_root": {
"total": 2483.370862400039,
"count": 64079,
"is_parallel": true,
"self": 1029.196658927098,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018406909998702758,
"count": 1,
"is_parallel": true,
"self": 0.0006314609995570208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001209230000313255,
"count": 8,
"is_parallel": true,
"self": 0.001209230000313255
}
}
},
"UnityEnvironment.step": {
"total": 0.04778520100012429,
"count": 1,
"is_parallel": true,
"self": 0.0005415440000433591,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044283600004746404,
"count": 1,
"is_parallel": true,
"self": 0.00044283600004746404
},
"communicator.exchange": {
"total": 0.04513358799999878,
"count": 1,
"is_parallel": true,
"self": 0.04513358799999878
},
"steps_from_proto": {
"total": 0.0016672330000346847,
"count": 1,
"is_parallel": true,
"self": 0.0004112540002552123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012559789997794724,
"count": 8,
"is_parallel": true,
"self": 0.0012559789997794724
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1454.1742034729411,
"count": 64078,
"is_parallel": true,
"self": 32.88964067094753,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.80764991890669,
"count": 64078,
"is_parallel": true,
"self": 23.80764991890669
},
"communicator.exchange": {
"total": 1300.251633544097,
"count": 64078,
"is_parallel": true,
"self": 1300.251633544097
},
"steps_from_proto": {
"total": 97.22527933898982,
"count": 64078,
"is_parallel": true,
"self": 23.811305957905915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.4139733810839,
"count": 512624,
"is_parallel": true,
"self": 73.4139733810839
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 773.1179715290673,
"count": 64079,
"self": 3.003165462081597,
"children": {
"process_trajectory": {
"total": 171.2858750749847,
"count": 64079,
"self": 171.05089970598465,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2349753690000398,
"count": 2,
"self": 0.2349753690000398
}
}
},
"_update_policy": {
"total": 598.828930992001,
"count": 454,
"self": 231.77363470703244,
"children": {
"TorchPPOOptimizer.update": {
"total": 367.05529628496856,
"count": 22809,
"self": 367.05529628496856
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.010000212583691e-07,
"count": 1,
"self": 9.010000212583691e-07
},
"TrainerController._save_models": {
"total": 0.08838169599994217,
"count": 1,
"self": 0.0014880009998705646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0868936950000716,
"count": 1,
"self": 0.0868936950000716
}
}
}
}
}
}
}