tux's picture
First Push
2d657eb
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3536791205406189,
"min": 0.3536791205406189,
"max": 1.4246598482131958,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10570.76171875,
"min": 10570.76171875,
"max": 43218.48046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989939.0,
"min": 29939.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989939.0,
"min": 29939.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4631487727165222,
"min": -0.09386790543794632,
"max": 0.5217593908309937,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 123.66072082519531,
"min": -22.90376853942871,
"max": 141.40713500976562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.005249334964901209,
"min": -0.005249334964901209,
"max": 0.5104305744171143,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -1.4015724658966064,
"min": -1.4015724658966064,
"max": 120.9720458984375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07071903655776711,
"min": 0.06677058105462753,
"max": 0.07368540704567135,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9900665118087395,
"min": 0.6585642141689895,
"max": 1.04937278151834,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014193617843072086,
"min": 0.0012021183416543663,
"max": 0.01577791357911857,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1987106498030092,
"min": 0.012021183416543664,
"max": 0.22089079010766,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.54391891396428e-06,
"min": 7.54391891396428e-06,
"max": 0.0002948755683748111,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010561486479549992,
"min": 0.00010561486479549992,
"max": 0.003759253946915399,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251460714285712,
"min": 0.10251460714285712,
"max": 0.1982918555555556,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352044999999998,
"min": 1.4352044999999998,
"max": 2.6530846000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002612092535714284,
"min": 0.0002612092535714284,
"max": 0.00982935637,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036569295499999975,
"min": 0.0036569295499999975,
"max": 0.12532315154,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009388496167957783,
"min": 0.009388496167957783,
"max": 0.39393576979637146,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1314389407634735,
"min": 0.1314389407634735,
"max": 3.545421838760376,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 399.36486486486484,
"min": 364.037037037037,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29553.0,
"min": 16738.0,
"max": 32361.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4924972799380083,
"min": -1.0000000521540642,
"max": 1.5618715799517102,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 110.44479871541262,
"min": -32.000001668930054,
"max": 126.51159797608852,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4924972799380083,
"min": -1.0000000521540642,
"max": 1.5618715799517102,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 110.44479871541262,
"min": -32.000001668930054,
"max": 126.51159797608852,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03887740106359627,
"min": 0.03654466102343128,
"max": 8.046779534396004,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8769276787061244,
"min": 2.8769276787061244,
"max": 136.79525208473206,
"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": "1687096125",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 Training2 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687098382"
},
"total": 2256.880584847,
"count": 1,
"self": 0.9760545819999606,
"children": {
"run_training.setup": {
"total": 0.045584334000011495,
"count": 1,
"self": 0.045584334000011495
},
"TrainerController.start_learning": {
"total": 2255.858945931,
"count": 1,
"self": 1.6107354689811473,
"children": {
"TrainerController._reset_env": {
"total": 3.9535759899999903,
"count": 1,
"self": 3.9535759899999903
},
"TrainerController.advance": {
"total": 2250.123924180019,
"count": 63778,
"self": 1.505916193007124,
"children": {
"env_step": {
"total": 1602.49778298,
"count": 63778,
"self": 1481.2403214369863,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.36158734901244,
"count": 63778,
"self": 5.091045727994128,
"children": {
"TorchPolicy.evaluate": {
"total": 115.27054162101831,
"count": 62557,
"self": 115.27054162101831
}
}
},
"workers": {
"total": 0.8958741940012374,
"count": 63778,
"self": 0.0,
"children": {
"worker_root": {
"total": 2250.196695784003,
"count": 63778,
"is_parallel": true,
"self": 891.7331898099587,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019291179999640917,
"count": 1,
"is_parallel": true,
"self": 0.0006426959999998871,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012864219999642046,
"count": 8,
"is_parallel": true,
"self": 0.0012864219999642046
}
}
},
"UnityEnvironment.step": {
"total": 0.052498699000011584,
"count": 1,
"is_parallel": true,
"self": 0.0005674270000213255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005210369999986142,
"count": 1,
"is_parallel": true,
"self": 0.0005210369999986142
},
"communicator.exchange": {
"total": 0.049369691999970655,
"count": 1,
"is_parallel": true,
"self": 0.049369691999970655
},
"steps_from_proto": {
"total": 0.002040543000020989,
"count": 1,
"is_parallel": true,
"self": 0.00038958299990099476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016509600001199942,
"count": 8,
"is_parallel": true,
"self": 0.0016509600001199942
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1358.4635059740444,
"count": 63777,
"is_parallel": true,
"self": 34.3106015080873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.884417651987008,
"count": 63777,
"is_parallel": true,
"self": 24.884417651987008
},
"communicator.exchange": {
"total": 1190.2516890579866,
"count": 63777,
"is_parallel": true,
"self": 1190.2516890579866
},
"steps_from_proto": {
"total": 109.01679775598353,
"count": 63777,
"is_parallel": true,
"self": 22.068798985954118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.94799877002941,
"count": 510216,
"is_parallel": true,
"self": 86.94799877002941
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 646.1202250070116,
"count": 63778,
"self": 2.9571255419862155,
"children": {
"process_trajectory": {
"total": 116.02260964002954,
"count": 63778,
"self": 115.75174388202919,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2708657580003546,
"count": 2,
"self": 0.2708657580003546
}
}
},
"_update_policy": {
"total": 527.1404898249959,
"count": 459,
"self": 336.50381863900515,
"children": {
"TorchPPOOptimizer.update": {
"total": 190.6366711859908,
"count": 22785,
"self": 190.6366711859908
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5760001588205341e-06,
"count": 1,
"self": 1.5760001588205341e-06
},
"TrainerController._save_models": {
"total": 0.1707087159998082,
"count": 1,
"self": 0.002121335999618168,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16858738000019002,
"count": 1,
"self": 0.16858738000019002
}
}
}
}
}
}
}