Kolosok's picture
First Push
df4dab8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8523352742195129,
"min": 0.8523352742195129,
"max": 2.8595588207244873,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8100.59423828125,
"min": 8100.59423828125,
"max": 29190.376953125,
"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": 13.03227710723877,
"min": 0.28418204188346863,
"max": 13.03227710723877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2541.2939453125,
"min": 55.131317138671875,
"max": 2627.012939453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06398339367696478,
"min": 0.06179484145817982,
"max": 0.07807925458862383,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2559335747078591,
"min": 0.24717936583271927,
"max": 0.35312402122683273,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2056451157904139,
"min": 0.10922139525920263,
"max": 0.2936773455026103,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8225804631616556,
"min": 0.4368855810368105,
"max": 1.460405775437168,
"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": 25.90909090909091,
"min": 2.9545454545454546,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 130.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 2.9545454545454546,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 130.0,
"max": 1407.0,
"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": "1764774721",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/envs/myenv/bin/mlagents-learn ml-agents/config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force",
"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": "1764775151"
},
"total": 430.00339565299987,
"count": 1,
"self": 0.4301744829998597,
"children": {
"run_training.setup": {
"total": 0.022539940999990904,
"count": 1,
"self": 0.022539940999990904
},
"TrainerController.start_learning": {
"total": 429.550681229,
"count": 1,
"self": 0.3224768950002499,
"children": {
"TrainerController._reset_env": {
"total": 2.9497545340000215,
"count": 1,
"self": 2.9497545340000215
},
"TrainerController.advance": {
"total": 426.20539279199977,
"count": 18192,
"self": 0.36510811199968884,
"children": {
"env_step": {
"total": 304.64155173201357,
"count": 18192,
"self": 237.87330586199903,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.56415978800362,
"count": 18192,
"self": 1.2084384509978463,
"children": {
"TorchPolicy.evaluate": {
"total": 65.35572133700578,
"count": 18192,
"self": 65.35572133700578
}
}
},
"workers": {
"total": 0.20408608201091738,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.9031848870022,
"count": 18192,
"is_parallel": true,
"self": 218.64572405098795,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004922364999970341,
"count": 1,
"is_parallel": true,
"self": 0.0034626450001269404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014597199998434007,
"count": 10,
"is_parallel": true,
"self": 0.0014597199998434007
}
}
},
"UnityEnvironment.step": {
"total": 0.03788797300001079,
"count": 1,
"is_parallel": true,
"self": 0.0006135190000122748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003839590000325188,
"count": 1,
"is_parallel": true,
"self": 0.0003839590000325188
},
"communicator.exchange": {
"total": 0.03420557499998722,
"count": 1,
"is_parallel": true,
"self": 0.03420557499998722
},
"steps_from_proto": {
"total": 0.0026849199999787743,
"count": 1,
"is_parallel": true,
"self": 0.00040822499988735217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002276695000091422,
"count": 10,
"is_parallel": true,
"self": 0.002276695000091422
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.25746083601427,
"count": 18191,
"is_parallel": true,
"self": 9.948897174004856,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.1848259820066005,
"count": 18191,
"is_parallel": true,
"self": 5.1848259820066005
},
"communicator.exchange": {
"total": 159.2221624809937,
"count": 18191,
"is_parallel": true,
"self": 159.2221624809937
},
"steps_from_proto": {
"total": 34.90157519900913,
"count": 18191,
"is_parallel": true,
"self": 6.547244420998368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.354330778010763,
"count": 181910,
"is_parallel": true,
"self": 28.354330778010763
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.19873294798651,
"count": 18192,
"self": 0.38623166398997455,
"children": {
"process_trajectory": {
"total": 25.657657881996784,
"count": 18192,
"self": 25.204673404996697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45298447700008637,
"count": 4,
"self": 0.45298447700008637
}
}
},
"_update_policy": {
"total": 95.15484340199976,
"count": 90,
"self": 40.1856412639944,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.96920213800536,
"count": 4587,
"self": 54.96920213800536
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.049998996284558e-07,
"count": 1,
"self": 8.049998996284558e-07
},
"TrainerController._save_models": {
"total": 0.07305620300007831,
"count": 1,
"self": 0.0007125419999738369,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07234366100010448,
"count": 1,
"self": 0.07234366100010448
}
}
}
}
}
}
}