andrewsamce's picture
First Push
e4b0695 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.712306499481201,
"min": 2.703087091445923,
"max": 2.8903496265411377,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4057.6103515625,
"min": 1902.973388671875,
"max": 4302.1474609375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 19992.0,
"min": 960.0,
"max": 19992.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4433648586273193,
"min": -0.050668444484472275,
"max": 2.4433648586273193,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 63.52748489379883,
"min": -0.7644834518432617,
"max": 63.52748489379883,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06796552486233778,
"min": 0.059130532847370444,
"max": 0.0753144042511635,
"count": 9
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06796552486233778,
"min": 0.059130532847370444,
"max": 0.0753144042511635,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2930185549399432,
"min": 0.09481009943228141,
"max": 0.2930185549399432,
"count": 9
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.2930185549399432,
"min": 0.09481009943228141,
"max": 0.2930185549399432,
"count": 9
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.2960098559999974e-05,
"min": 1.2960098559999974e-05,
"max": 0.00080496001056,
"count": 9
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.2960098559999974e-05,
"min": 1.2960098559999974e-05,
"max": 0.00080496001056,
"count": 9
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10144,
"min": 0.10144,
"max": 0.18944000000000003,
"count": 9
},
"SnowballTarget.Policy.Beta.mean": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Policy.Beta.sum": {
"value": 8.185599999999986e-05,
"min": 8.185599999999986e-05,
"max": 0.0044730559999999996,
"count": 9
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 9
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 2189.0,
"min": 2189.0,
"max": 2189.0,
"count": 9
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 7.636363636363637,
"min": 2.8181818181818183,
"max": 9.090909090909092,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 84.0,
"min": 4.0,
"max": 100.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 7.636363636363637,
"min": 2.8181818181818183,
"max": 9.090909090909092,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 84.0,
"min": 4.0,
"max": 100.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1752092041",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752092089"
},
"total": 47.80252071299992,
"count": 1,
"self": 0.7836711940001351,
"children": {
"run_training.setup": {
"total": 0.021527060999915193,
"count": 1,
"self": 0.021527060999915193
},
"TrainerController.start_learning": {
"total": 46.99732245799987,
"count": 1,
"self": 0.03506993299401984,
"children": {
"TrainerController._reset_env": {
"total": 3.1066365770000175,
"count": 1,
"self": 3.1066365770000175
},
"TrainerController.advance": {
"total": 43.71983982100619,
"count": 1864,
"self": 0.03755262200979814,
"children": {
"env_step": {
"total": 31.002341879000824,
"count": 1864,
"self": 23.688766983991627,
"children": {
"SubprocessEnvManager._take_step": {
"total": 7.292808291002302,
"count": 1864,
"self": 0.12554376799766942,
"children": {
"TorchPolicy.evaluate": {
"total": 7.167264523004633,
"count": 1864,
"self": 7.167264523004633
}
}
},
"workers": {
"total": 0.02076660400689434,
"count": 1864,
"self": 0.0,
"children": {
"worker_root": {
"total": 46.595673720003106,
"count": 1864,
"is_parallel": true,
"self": 25.7769956190034,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004675518000112788,
"count": 1,
"is_parallel": true,
"self": 0.003321983000205364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013535349999074242,
"count": 10,
"is_parallel": true,
"self": 0.0013535349999074242
}
}
},
"UnityEnvironment.step": {
"total": 0.05095431500012637,
"count": 1,
"is_parallel": true,
"self": 0.0006255010000586481,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003987019999840413,
"count": 1,
"is_parallel": true,
"self": 0.0003987019999840413
},
"communicator.exchange": {
"total": 0.047850280999909955,
"count": 1,
"is_parallel": true,
"self": 0.047850280999909955
},
"steps_from_proto": {
"total": 0.0020798310001737264,
"count": 1,
"is_parallel": true,
"self": 0.0003871470000831323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001692684000090594,
"count": 10,
"is_parallel": true,
"self": 0.001692684000090594
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 20.818678100999705,
"count": 1863,
"is_parallel": true,
"self": 1.0041487060007057,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.5539290709950819,
"count": 1863,
"is_parallel": true,
"self": 0.5539290709950819
},
"communicator.exchange": {
"total": 15.981382143004566,
"count": 1863,
"is_parallel": true,
"self": 15.981382143004566
},
"steps_from_proto": {
"total": 3.279218180999351,
"count": 1863,
"is_parallel": true,
"self": 0.5771895879659041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.7020285930334467,
"count": 18630,
"is_parallel": true,
"self": 2.7020285930334467
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 12.679945319995568,
"count": 1864,
"self": 0.04256250699540942,
"children": {
"process_trajectory": {
"total": 3.160152591999804,
"count": 1864,
"self": 2.721208565999632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.438944026000172,
"count": 4,
"self": 0.438944026000172
}
}
},
"_update_policy": {
"total": 9.477230221000355,
"count": 9,
"self": 3.8169123640016096,
"children": {
"TorchPPOOptimizer.update": {
"total": 5.660317856998745,
"count": 456,
"self": 5.660317856998745
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.309999788645655e-06,
"count": 1,
"self": 1.309999788645655e-06
},
"TrainerController._save_models": {
"total": 0.13577481699985583,
"count": 1,
"self": 0.0012377209998248873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13453709600003094,
"count": 1,
"self": 0.13453709600003094
}
}
}
}
}
}
}