Valencio's picture
First Push of Pyramids env
4896b0e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.36531615257263184,
"min": 0.35316231846809387,
"max": 1.4072073698043823,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11058.8505859375,
"min": 10476.20703125,
"max": 42689.04296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989969.0,
"min": 29895.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989969.0,
"min": 29895.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6748013496398926,
"min": -0.10251276940107346,
"max": 0.6748013496398926,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 195.6923828125,
"min": -24.2955265045166,
"max": 195.6923828125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.022393934428691864,
"min": -0.008409584872424603,
"max": 0.6055624485015869,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.494240760803223,
"min": -2.194901704788208,
"max": 143.51829528808594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0690110051835377,
"min": 0.06505767345411836,
"max": 0.07445365060970321,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9661540725695278,
"min": 0.5956292048776257,
"max": 1.0618362873210572,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01467655706905394,
"min": 0.0007257953923035478,
"max": 0.016466419004747934,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20547179896675516,
"min": 0.008709544707642574,
"max": 0.23627293032711585,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.37150468572143e-06,
"min": 7.37150468572143e-06,
"max": 0.000294762676745775,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010320106560010002,
"min": 0.00010320106560010002,
"max": 0.0036330199889933997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10245713571428572,
"min": 0.10245713571428572,
"max": 0.198254225,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4343999,
"min": 1.4343999,
"max": 2.6172996,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025546785785714296,
"min": 0.00025546785785714296,
"max": 0.009825597077500001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003576550010000001,
"min": 0.003576550010000001,
"max": 0.12111955934,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014778071083128452,
"min": 0.013881360180675983,
"max": 0.540066123008728,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20689299702644348,
"min": 0.19433903694152832,
"max": 4.320528984069824,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 292.79,
"min": 292.79,
"max": 993.1875,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29279.0,
"min": 17333.0,
"max": 32079.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6871999821811914,
"min": -0.9315812999848276,
"max": 1.6871999821811914,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 168.71999821811914,
"min": -29.810601599514484,
"max": 168.71999821811914,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6871999821811914,
"min": -0.9315812999848276,
"max": 1.6871999821811914,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 168.71999821811914,
"min": -29.810601599514484,
"max": 168.71999821811914,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.044010160803009055,
"min": 0.044010160803009055,
"max": 12.336932001842392,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.401016080300906,
"min": 4.401016080300906,
"max": 222.06477603316307,
"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": "1765146486",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765148781"
},
"total": 2295.698784864,
"count": 1,
"self": 0.4798286459999872,
"children": {
"run_training.setup": {
"total": 0.03496292199997697,
"count": 1,
"self": 0.03496292199997697
},
"TrainerController.start_learning": {
"total": 2295.183993296,
"count": 1,
"self": 1.3197711869961495,
"children": {
"TrainerController._reset_env": {
"total": 2.0590287320001153,
"count": 1,
"self": 2.0590287320001153
},
"TrainerController.advance": {
"total": 2291.7265200200036,
"count": 64162,
"self": 1.4019757579626457,
"children": {
"env_step": {
"total": 1622.545226377024,
"count": 64162,
"self": 1472.9541040870013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.791206857009,
"count": 64162,
"self": 4.6623665100360085,
"children": {
"TorchPolicy.evaluate": {
"total": 144.128840346973,
"count": 62569,
"self": 144.128840346973
}
}
},
"workers": {
"total": 0.7999154330136662,
"count": 64162,
"self": 0.0,
"children": {
"worker_root": {
"total": 2288.8402719520373,
"count": 64162,
"is_parallel": true,
"self": 933.6521910531446,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016881920000741957,
"count": 1,
"is_parallel": true,
"self": 0.0005420850000064092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011461070000677864,
"count": 8,
"is_parallel": true,
"self": 0.0011461070000677864
}
}
},
"UnityEnvironment.step": {
"total": 0.054373865000115984,
"count": 1,
"is_parallel": true,
"self": 0.0005877549999695475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004804850000255101,
"count": 1,
"is_parallel": true,
"self": 0.0004804850000255101
},
"communicator.exchange": {
"total": 0.051357220999989295,
"count": 1,
"is_parallel": true,
"self": 0.051357220999989295
},
"steps_from_proto": {
"total": 0.0019484040001316316,
"count": 1,
"is_parallel": true,
"self": 0.0003968450007505453,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015515589993810863,
"count": 8,
"is_parallel": true,
"self": 0.0015515589993810863
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1355.1880808988926,
"count": 64161,
"is_parallel": true,
"self": 34.69470163283472,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.671487786969237,
"count": 64161,
"is_parallel": true,
"self": 24.671487786969237
},
"communicator.exchange": {
"total": 1182.9244445850472,
"count": 64161,
"is_parallel": true,
"self": 1182.9244445850472
},
"steps_from_proto": {
"total": 112.89744689404142,
"count": 64161,
"is_parallel": true,
"self": 23.24197369819649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 89.65547319584493,
"count": 513288,
"is_parallel": true,
"self": 89.65547319584493
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 667.7793178850172,
"count": 64162,
"self": 2.5811499319950144,
"children": {
"process_trajectory": {
"total": 128.89582004702334,
"count": 64162,
"self": 128.7022748740228,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19354517300052976,
"count": 2,
"self": 0.19354517300052976
}
}
},
"_update_policy": {
"total": 536.3023479059989,
"count": 460,
"self": 299.2870182269903,
"children": {
"TorchPPOOptimizer.update": {
"total": 237.01532967900857,
"count": 22845,
"self": 237.01532967900857
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.021000116452342e-06,
"count": 1,
"self": 1.021000116452342e-06
},
"TrainerController._save_models": {
"total": 0.07867233600018153,
"count": 1,
"self": 0.0010054910003418627,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07766684499983967,
"count": 1,
"self": 0.07766684499983967
}
}
}
}
}
}
}