Neomedallion's picture
First Push Snowball
775c336 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0791633129119873,
"min": 1.0791633129119873,
"max": 2.8602442741394043,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10303.8515625,
"min": 10303.8515625,
"max": 29291.76171875,
"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": 12.676441192626953,
"min": 0.3394342064857483,
"max": 12.676441192626953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.906005859375,
"min": 65.85023498535156,
"max": 2553.064453125,
"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.Losses.PolicyLoss.mean": {
"value": 0.0635831177748746,
"min": 0.06070934183502972,
"max": 0.07717526687809047,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2543324710994984,
"min": 0.24830674517593876,
"max": 0.37759567633203883,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2023734346616502,
"min": 0.11972034007639569,
"max": 0.3019342250099369,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8094937386466008,
"min": 0.47888136030558276,
"max": 1.5096711250496844,
"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.CumulativeReward.mean": {
"value": 25.454545454545453,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 142.0,
"max": 1372.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 142.0,
"max": 1372.0,
"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": "1709533247",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709533688"
},
"total": 441.66700699700004,
"count": 1,
"self": 0.44903183800010993,
"children": {
"run_training.setup": {
"total": 0.05743916300002638,
"count": 1,
"self": 0.05743916300002638
},
"TrainerController.start_learning": {
"total": 441.1605359959999,
"count": 1,
"self": 0.56619163701248,
"children": {
"TrainerController._reset_env": {
"total": 3.2469858929999873,
"count": 1,
"self": 3.2469858929999873
},
"TrainerController.advance": {
"total": 437.2557033159875,
"count": 18199,
"self": 0.27211881300081586,
"children": {
"env_step": {
"total": 436.9835845029867,
"count": 18199,
"self": 283.3381605419686,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.36906375500644,
"count": 18199,
"self": 1.433246528992413,
"children": {
"TorchPolicy.evaluate": {
"total": 151.93581722601402,
"count": 18199,
"self": 151.93581722601402
}
}
},
"workers": {
"total": 0.27636020601164546,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.97358176301066,
"count": 18199,
"is_parallel": true,
"self": 217.4174278400218,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008080318999986957,
"count": 1,
"is_parallel": true,
"self": 0.003855709000049501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0042246099999374565,
"count": 10,
"is_parallel": true,
"self": 0.0042246099999374565
}
}
},
"UnityEnvironment.step": {
"total": 0.037608023000075264,
"count": 1,
"is_parallel": true,
"self": 0.0007486430001790723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044284599994171003,
"count": 1,
"is_parallel": true,
"self": 0.00044284599994171003
},
"communicator.exchange": {
"total": 0.03417119300002014,
"count": 1,
"is_parallel": true,
"self": 0.03417119300002014
},
"steps_from_proto": {
"total": 0.002245340999934342,
"count": 1,
"is_parallel": true,
"self": 0.0006003779997172387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016449630002171034,
"count": 10,
"is_parallel": true,
"self": 0.0016449630002171034
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.55615392298887,
"count": 18198,
"is_parallel": true,
"self": 10.789061692971018,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.359609509008692,
"count": 18198,
"is_parallel": true,
"self": 5.359609509008692
},
"communicator.exchange": {
"total": 172.98474071401245,
"count": 18198,
"is_parallel": true,
"self": 172.98474071401245
},
"steps_from_proto": {
"total": 33.422742006996714,
"count": 18198,
"is_parallel": true,
"self": 6.199661495986561,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.223080511010153,
"count": 181980,
"is_parallel": true,
"self": 27.223080511010153
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011447700012467976,
"count": 1,
"self": 0.00011447700012467976,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 431.78391755504595,
"count": 667034,
"is_parallel": true,
"self": 13.943942244089726,
"children": {
"process_trajectory": {
"total": 238.2716124159566,
"count": 667034,
"is_parallel": true,
"self": 237.62363260495658,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6479798110000274,
"count": 4,
"is_parallel": true,
"self": 0.6479798110000274
}
}
},
"_update_policy": {
"total": 179.5683628949996,
"count": 90,
"is_parallel": true,
"self": 51.03032260800205,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.53804028699756,
"count": 4587,
"is_parallel": true,
"self": 128.53804028699756
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09154067299982671,
"count": 1,
"self": 0.0009609459998500824,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09057972699997663,
"count": 1,
"self": 0.09057972699997663
}
}
}
}
}
}
}