pineapplechoco's picture
First Push
38c1bb6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7467113733291626,
"min": 0.7467113733291626,
"max": 2.8584682941436768,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7096.7451171875,
"min": 7096.7451171875,
"max": 29179.244140625,
"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": 10.991752624511719,
"min": 0.3259613513946533,
"max": 10.991752624511719,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2143.391845703125,
"min": 63.23650360107422,
"max": 2233.88525390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07125443142899267,
"min": 0.06473145038405931,
"max": 0.07354157737738169,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28501772571597067,
"min": 0.25892580153623723,
"max": 0.3677078868869085,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16377083723451577,
"min": 0.1372799065201452,
"max": 0.258014765440249,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6550833489380631,
"min": 0.5491196260805808,
"max": 1.2900738272012449,
"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": 21.068181818181817,
"min": 3.6818181818181817,
"max": 21.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 927.0,
"min": 162.0,
"max": 1200.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.068181818181817,
"min": 3.6818181818181817,
"max": 21.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 927.0,
"min": 162.0,
"max": 1200.0,
"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": "1761579050",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
"command_line_arguments": "./ml-agents/mlagents/trainers/learn.py ./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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1761579515"
},
"total": 464.7299811390001,
"count": 1,
"self": 0.4306415260001586,
"children": {
"run_training.setup": {
"total": 0.020435698000028424,
"count": 1,
"self": 0.020435698000028424
},
"TrainerController.start_learning": {
"total": 464.2789039149999,
"count": 1,
"self": 0.41082283599780567,
"children": {
"TrainerController._reset_env": {
"total": 3.3126558079999313,
"count": 1,
"self": 3.3126558079999313
},
"TrainerController.advance": {
"total": 460.476295170002,
"count": 18192,
"self": 0.4407861590278799,
"children": {
"env_step": {
"total": 338.5648555769984,
"count": 18192,
"self": 264.3005085760095,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.01261374599198,
"count": 18192,
"self": 1.3499740410120467,
"children": {
"TorchPolicy.evaluate": {
"total": 72.66263970497994,
"count": 18192,
"self": 72.66263970497994
}
}
},
"workers": {
"total": 0.2517332549969069,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.42993477199616,
"count": 18192,
"is_parallel": true,
"self": 230.60050455699366,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063821840000173324,
"count": 1,
"is_parallel": true,
"self": 0.004197707999992417,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021844760000249153,
"count": 10,
"is_parallel": true,
"self": 0.0021844760000249153
}
}
},
"UnityEnvironment.step": {
"total": 0.03683524500002022,
"count": 1,
"is_parallel": true,
"self": 0.0005594969998128363,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042363400007161545,
"count": 1,
"is_parallel": true,
"self": 0.00042363400007161545
},
"communicator.exchange": {
"total": 0.033897740000043086,
"count": 1,
"is_parallel": true,
"self": 0.033897740000043086
},
"steps_from_proto": {
"total": 0.0019543740000926846,
"count": 1,
"is_parallel": true,
"self": 0.00038716800008842256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001567206000004262,
"count": 10,
"is_parallel": true,
"self": 0.001567206000004262
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.8294302150025,
"count": 18191,
"is_parallel": true,
"self": 10.546382307033582,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.797750910969853,
"count": 18191,
"is_parallel": true,
"self": 5.797750910969853
},
"communicator.exchange": {
"total": 176.3437066539983,
"count": 18191,
"is_parallel": true,
"self": 176.3437066539983
},
"steps_from_proto": {
"total": 39.14159034300076,
"count": 18191,
"is_parallel": true,
"self": 7.1262508419988535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.015339501001904,
"count": 181910,
"is_parallel": true,
"self": 32.015339501001904
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.47065343397571,
"count": 18192,
"self": 0.543454399970642,
"children": {
"process_trajectory": {
"total": 27.800162828004545,
"count": 18192,
"self": 27.40912503600464,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3910377919999064,
"count": 4,
"self": 0.3910377919999064
}
}
},
"_update_policy": {
"total": 93.12703620600053,
"count": 90,
"self": 37.98204444499822,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.1449917610023,
"count": 4587,
"self": 55.1449917610023
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.340000476891873e-07,
"count": 1,
"self": 8.340000476891873e-07
},
"TrainerController._save_models": {
"total": 0.07912926700009848,
"count": 1,
"self": 0.0006893690001561481,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07843989799994233,
"count": 1,
"self": 0.07843989799994233
}
}
}
}
}
}
}