Dharkelf's picture
First Push
4c9939b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.379440039396286,
"min": 0.37580257654190063,
"max": 1.4002320766448975,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11340.7041015625,
"min": 11280.08984375,
"max": 42477.44140625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.672539234161377,
"min": -0.11441444605588913,
"max": 0.672539234161377,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 189.65606689453125,
"min": -27.4594669342041,
"max": 189.65606689453125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.019445322453975677,
"min": 0.010138855315744877,
"max": 0.3171239197254181,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.483581066131592,
"min": 2.5448527336120605,
"max": 75.15837097167969,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06900834671839783,
"min": 0.06519335990516321,
"max": 0.07185937618124313,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9661168540575695,
"min": 0.4701841024232991,
"max": 1.0446740084541186,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015674714653869163,
"min": 0.0008746194644267421,
"max": 0.017249880499856714,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21944600515416826,
"min": 0.0061223362509871945,
"max": 0.2461226639376643,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.486468933114286e-06,
"min": 7.486468933114286e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001048105650636,
"min": 0.0001048105650636,
"max": 0.0035087084304305993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249545714285714,
"min": 0.10249545714285714,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349364,
"min": 1.3691136000000002,
"max": 2.5695694000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025929616857142863,
"min": 0.00025929616857142863,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036301463600000006,
"min": 0.0036301463600000006,
"max": 0.11697998306,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011384449899196625,
"min": 0.011278988793492317,
"max": 0.4428793489933014,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15938229858875275,
"min": 0.1579669713973999,
"max": 3.1001553535461426,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 288.5049504950495,
"min": 288.5049504950495,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29139.0,
"min": 15984.0,
"max": 33652.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6936799838393926,
"min": -1.0000000521540642,
"max": 1.6936799838393926,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 169.36799838393927,
"min": -32.000001668930054,
"max": 178.5055983364582,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6936799838393926,
"min": -1.0000000521540642,
"max": 1.6936799838393926,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 169.36799838393927,
"min": -32.000001668930054,
"max": 178.5055983364582,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03358118394840858,
"min": 0.03358118394840858,
"max": 8.66899473592639,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.358118394840858,
"min": 3.278391066356562,
"max": 138.70391577482224,
"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": "1673516988",
"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": "1673519157"
},
"total": 2168.712363431,
"count": 1,
"self": 0.4412405809998745,
"children": {
"run_training.setup": {
"total": 0.11316256200001362,
"count": 1,
"self": 0.11316256200001362
},
"TrainerController.start_learning": {
"total": 2168.157960288,
"count": 1,
"self": 1.2753127300175038,
"children": {
"TrainerController._reset_env": {
"total": 7.344601271999977,
"count": 1,
"self": 7.344601271999977
},
"TrainerController.advance": {
"total": 2159.446222906983,
"count": 63944,
"self": 1.3818564589182643,
"children": {
"env_step": {
"total": 1474.0908459910368,
"count": 63944,
"self": 1364.2711079730088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.02053242901331,
"count": 63944,
"self": 4.497250520067894,
"children": {
"TorchPolicy.evaluate": {
"total": 104.52328190894542,
"count": 62549,
"self": 35.32565314291003,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.1976287660354,
"count": 62549,
"self": 69.1976287660354
}
}
}
}
},
"workers": {
"total": 0.7992055890146617,
"count": 63944,
"self": 0.0,
"children": {
"worker_root": {
"total": 2163.3873002919627,
"count": 63944,
"is_parallel": true,
"self": 904.6960415089586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005535167999994428,
"count": 1,
"is_parallel": true,
"self": 0.0032592950000207566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022758729999736715,
"count": 8,
"is_parallel": true,
"self": 0.0022758729999736715
}
}
},
"UnityEnvironment.step": {
"total": 0.051139208999984476,
"count": 1,
"is_parallel": true,
"self": 0.0005385230000456431,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047426099996528137,
"count": 1,
"is_parallel": true,
"self": 0.00047426099996528137
},
"communicator.exchange": {
"total": 0.04821441199999299,
"count": 1,
"is_parallel": true,
"self": 0.04821441199999299
},
"steps_from_proto": {
"total": 0.0019120129999805613,
"count": 1,
"is_parallel": true,
"self": 0.00047592600003554253,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014360869999450188,
"count": 8,
"is_parallel": true,
"self": 0.0014360869999450188
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1258.691258783004,
"count": 63943,
"is_parallel": true,
"self": 28.66401909593992,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.970239277019402,
"count": 63943,
"is_parallel": true,
"self": 24.970239277019402
},
"communicator.exchange": {
"total": 1103.882816778038,
"count": 63943,
"is_parallel": true,
"self": 1103.882816778038
},
"steps_from_proto": {
"total": 101.1741836320067,
"count": 63943,
"is_parallel": true,
"self": 23.84452879992068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.32965483208602,
"count": 511544,
"is_parallel": true,
"self": 77.32965483208602
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 683.9735204570283,
"count": 63944,
"self": 2.3844614239835664,
"children": {
"process_trajectory": {
"total": 155.76348132304554,
"count": 63944,
"self": 155.55787324004507,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2056080830004703,
"count": 2,
"self": 0.2056080830004703
}
}
},
"_update_policy": {
"total": 525.8255777099992,
"count": 449,
"self": 202.09826253600892,
"children": {
"TorchPPOOptimizer.update": {
"total": 323.72731517399023,
"count": 22863,
"self": 323.72731517399023
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.739997040014714e-07,
"count": 1,
"self": 9.739997040014714e-07
},
"TrainerController._save_models": {
"total": 0.0918224049996752,
"count": 1,
"self": 0.0014455379996434203,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09037686700003178,
"count": 1,
"self": 0.09037686700003178
}
}
}
}
}
}
}