Malgesw's picture
Pushed first SnowballTarget model
ceeb3e2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8692088723182678,
"min": 0.8692088723182678,
"max": 2.8603968620300293,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8260.9609375,
"min": 8260.9609375,
"max": 29198.931640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.543521881103516,
"min": 0.3136991560459137,
"max": 12.543521881103516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2445.98681640625,
"min": 60.857635498046875,
"max": 2552.46923828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06484843638164045,
"min": 0.06278644516988767,
"max": 0.07491352678020942,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2593937455265618,
"min": 0.2538409605830584,
"max": 0.36030109780475356,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20832314605222027,
"min": 0.09893992459333009,
"max": 0.2779710931959105,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8332925842088811,
"min": 0.39575969837332037,
"max": 1.332249073421254,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.84090909090909,
"min": 2.9318181818181817,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 129.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 2.9318181818181817,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 129.0,
"max": 1364.0,
"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
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1769214986",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/kaneki/miniconda3/envs/deepRL2/bin/mlagents-learn ../unit1/ml-agents/config/ppo/SnowballTarget.yaml --env=../unit1/trained-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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769215215"
},
"total": 229.59009693799987,
"count": 1,
"self": 0.21855786999992688,
"children": {
"run_training.setup": {
"total": 0.021495338000022457,
"count": 1,
"self": 0.021495338000022457
},
"TrainerController.start_learning": {
"total": 229.35004372999992,
"count": 1,
"self": 0.25174701798107435,
"children": {
"TrainerController._reset_env": {
"total": 2.002047607999998,
"count": 1,
"self": 2.002047607999998
},
"TrainerController.advance": {
"total": 227.03374502201882,
"count": 18192,
"self": 0.23274356902766158,
"children": {
"env_step": {
"total": 156.54321544300876,
"count": 18192,
"self": 112.370699600021,
"children": {
"SubprocessEnvManager._take_step": {
"total": 44.014465376986664,
"count": 18192,
"self": 0.6671456839951588,
"children": {
"TorchPolicy.evaluate": {
"total": 43.347319692991505,
"count": 18192,
"self": 43.347319692991505
}
}
},
"workers": {
"total": 0.15805046600110018,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 228.85726540201154,
"count": 18192,
"is_parallel": true,
"self": 131.0983497250171,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011955720000287329,
"count": 1,
"is_parallel": true,
"self": 0.0003628510004318741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008327209995968587,
"count": 10,
"is_parallel": true,
"self": 0.0008327209995968587
}
}
},
"UnityEnvironment.step": {
"total": 0.01573100699999941,
"count": 1,
"is_parallel": true,
"self": 0.00020335000010618387,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021455999990394048,
"count": 1,
"is_parallel": true,
"self": 0.00021455999990394048
},
"communicator.exchange": {
"total": 0.014615785999922082,
"count": 1,
"is_parallel": true,
"self": 0.014615785999922082
},
"steps_from_proto": {
"total": 0.0006973110000672023,
"count": 1,
"is_parallel": true,
"self": 0.00017573000025095098,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005215809998162513,
"count": 10,
"is_parallel": true,
"self": 0.0005215809998162513
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 97.75891567699443,
"count": 18191,
"is_parallel": true,
"self": 3.952655257986862,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.3571205040027507,
"count": 18191,
"is_parallel": true,
"self": 2.3571205040027507
},
"communicator.exchange": {
"total": 79.10230650900212,
"count": 18191,
"is_parallel": true,
"self": 79.10230650900212
},
"steps_from_proto": {
"total": 12.346833406002702,
"count": 18191,
"is_parallel": true,
"self": 2.5644396100235554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.782393795979146,
"count": 181910,
"is_parallel": true,
"self": 9.782393795979146
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70.2577860099824,
"count": 18192,
"self": 0.34179654996603404,
"children": {
"process_trajectory": {
"total": 15.879627463017869,
"count": 18192,
"self": 15.630827879018057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24879958399981206,
"count": 4,
"self": 0.24879958399981206
}
}
},
"_update_policy": {
"total": 54.036361996998494,
"count": 90,
"self": 21.848902700994017,
"children": {
"TorchPPOOptimizer.update": {
"total": 32.18745929600448,
"count": 4587,
"self": 32.18745929600448
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.10000142842182e-07,
"count": 1,
"self": 6.10000142842182e-07
},
"TrainerController._save_models": {
"total": 0.06250347199988937,
"count": 1,
"self": 0.0006644179998147592,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06183905400007461,
"count": 1,
"self": 0.06183905400007461
}
}
}
}
}
}
}