Revv8's picture
First Push
5a89cf9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8354975581169128,
"min": 0.8294440507888794,
"max": 2.5645792484283447,
"count": 19
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8014.0927734375,
"min": 8014.0927734375,
"max": 23625.62109375,
"count": 19
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 19968.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 19968.0,
"max": 199984.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.961666107177734,
"min": 1.846458911895752,
"max": 12.961666107177734,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2657.1416015625,
"min": 108.94107818603516,
"max": 2657.1416015625,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06460846437143582,
"min": 0.06046980756207132,
"max": 0.07371379257578975,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.32304232185717907,
"min": 0.06465277752916639,
"max": 0.3556739848974009,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1857653231013055,
"min": 0.1857653231013055,
"max": 0.31603154726326466,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9288266155065275,
"min": 0.31603154726326466,
"max": 1.4239543512755748,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.620097459999994e-06,
"min": 7.620097459999994e-06,
"max": 0.00027162000946,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.810048729999997e-05,
"min": 3.810048729999997e-05,
"max": 0.0013086000637999998,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10254,
"min": 0.10254,
"max": 0.19054000000000001,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5127,
"min": 0.19054000000000001,
"max": 0.9362,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001367459999999999,
"min": 0.0001367459999999999,
"max": 0.004527945999999999,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0006837299999999995,
"min": 0.0006837299999999995,
"max": 0.02181638,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 19
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 2189.0,
"max": 10945.0,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.78181818181818,
"min": 9.181818181818182,
"max": 25.78181818181818,
"count": 19
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1418.0,
"min": 101.0,
"max": 1418.0,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.78181818181818,
"min": 9.181818181818182,
"max": 25.78181818181818,
"count": 19
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1418.0,
"min": 101.0,
"max": 1418.0,
"count": 19
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1777295364",
"python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"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": "1777295925"
},
"total": 561.2359936849998,
"count": 1,
"self": 0.9513471199988999,
"children": {
"run_training.setup": {
"total": 0.027780918000644306,
"count": 1,
"self": 0.027780918000644306
},
"TrainerController.start_learning": {
"total": 560.2568656470003,
"count": 1,
"self": 0.587524446000316,
"children": {
"TrainerController._reset_env": {
"total": 2.104993065000599,
"count": 1,
"self": 2.104993065000599
},
"TrainerController.advance": {
"total": 557.4497666309999,
"count": 16664,
"self": 0.6030975679950643,
"children": {
"env_step": {
"total": 396.9355102461268,
"count": 16664,
"self": 341.8756260271575,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.66314560394039,
"count": 16664,
"self": 2.051443569042931,
"children": {
"TorchPolicy.evaluate": {
"total": 52.61170203489746,
"count": 16664,
"self": 52.61170203489746
}
}
},
"workers": {
"total": 0.3967386150288803,
"count": 16664,
"self": 0.0,
"children": {
"worker_root": {
"total": 557.1841120379731,
"count": 16664,
"is_parallel": true,
"self": 262.0590502140103,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002366155000345316,
"count": 1,
"is_parallel": true,
"self": 0.0006639780012847041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017021769990606117,
"count": 10,
"is_parallel": true,
"self": 0.0017021769990606117
}
}
},
"UnityEnvironment.step": {
"total": 0.054092532000140636,
"count": 1,
"is_parallel": true,
"self": 0.0007476280006812885,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004832499998883577,
"count": 1,
"is_parallel": true,
"self": 0.0004832499998883577
},
"communicator.exchange": {
"total": 0.04422045100000105,
"count": 1,
"is_parallel": true,
"self": 0.04422045100000105
},
"steps_from_proto": {
"total": 0.008641202999569941,
"count": 1,
"is_parallel": true,
"self": 0.0005580739980359795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008083129001533962,
"count": 10,
"is_parallel": true,
"self": 0.008083129001533962
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 295.1250618239628,
"count": 16663,
"is_parallel": true,
"self": 13.319300560050578,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.430884576010612,
"count": 16663,
"is_parallel": true,
"self": 7.430884576010612
},
"communicator.exchange": {
"total": 226.61178362196824,
"count": 16663,
"is_parallel": true,
"self": 226.61178362196824
},
"steps_from_proto": {
"total": 47.76309306593339,
"count": 16663,
"is_parallel": true,
"self": 8.691494328834779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.07159873709861,
"count": 166630,
"is_parallel": true,
"self": 39.07159873709861
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 159.91115881687801,
"count": 16664,
"self": 0.7658030419661372,
"children": {
"process_trajectory": {
"total": 29.966465980919565,
"count": 16664,
"self": 29.507753163919006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4587128170005599,
"count": 4,
"self": 0.4587128170005599
}
}
},
"_update_policy": {
"total": 129.1788897939923,
"count": 83,
"self": 47.87249548197633,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.30639431201598,
"count": 4230,
"self": 81.30639431201598
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4469997040578164e-06,
"count": 1,
"self": 1.4469997040578164e-06
},
"TrainerController._save_models": {
"total": 0.114580057999774,
"count": 1,
"self": 0.0018646319995241356,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11271542600024986,
"count": 1,
"self": 0.11271542600024986
}
}
}
}
}
}
}