shubhamagarwal92's picture
First Push
3ca9f85
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.022096872329712,
"min": 1.0161384344100952,
"max": 2.86085844039917,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9770.2236328125,
"min": 9770.2236328125,
"max": 29298.05078125,
"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": 12.852416038513184,
"min": 0.30092060565948486,
"max": 12.852416038513184,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.22119140625,
"min": 58.378597259521484,
"max": 2617.0517578125,
"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": 0.06701599070391454,
"min": 0.06421486235031967,
"max": 0.07563485576867926,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26806396281565814,
"min": 0.26806396281565814,
"max": 0.36980327501791466,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20410954433621145,
"min": 0.11730025373810135,
"max": 0.2840553603920282,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8164381773448458,
"min": 0.4692010149524054,
"max": 1.420276801960141,
"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": 25.204545454545453,
"min": 3.409090909090909,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 150.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.409090909090909,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 150.0,
"max": 1412.0,
"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": "1691171249",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1691171737"
},
"total": 488.150722598,
"count": 1,
"self": 0.4352143490000344,
"children": {
"run_training.setup": {
"total": 0.06970316900003581,
"count": 1,
"self": 0.06970316900003581
},
"TrainerController.start_learning": {
"total": 487.64580507999995,
"count": 1,
"self": 0.5874407699891435,
"children": {
"TrainerController._reset_env": {
"total": 7.464575403000026,
"count": 1,
"self": 7.464575403000026
},
"TrainerController.advance": {
"total": 479.4528001540108,
"count": 18203,
"self": 0.29731233100824284,
"children": {
"env_step": {
"total": 479.15548782300255,
"count": 18203,
"self": 350.6425204850001,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.21209596000006,
"count": 18203,
"self": 1.8399591209978325,
"children": {
"TorchPolicy.evaluate": {
"total": 126.37213683900222,
"count": 18203,
"self": 126.37213683900222
}
}
},
"workers": {
"total": 0.30087137800239816,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.16119717999766,
"count": 18203,
"is_parallel": true,
"self": 229.95618570798752,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00927056300008644,
"count": 1,
"is_parallel": true,
"self": 0.006780450999940513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024901120001459276,
"count": 10,
"is_parallel": true,
"self": 0.0024901120001459276
}
}
},
"UnityEnvironment.step": {
"total": 0.044359427000017604,
"count": 1,
"is_parallel": true,
"self": 0.0006196110000473709,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044647999993685517,
"count": 1,
"is_parallel": true,
"self": 0.00044647999993685517
},
"communicator.exchange": {
"total": 0.04118678200006798,
"count": 1,
"is_parallel": true,
"self": 0.04118678200006798
},
"steps_from_proto": {
"total": 0.0021065539999653993,
"count": 1,
"is_parallel": true,
"self": 0.0003821059998472265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017244480001181728,
"count": 10,
"is_parallel": true,
"self": 0.0017244480001181728
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 256.20501147201014,
"count": 18202,
"is_parallel": true,
"self": 10.767726717022015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.401497331991209,
"count": 18202,
"is_parallel": true,
"self": 5.401497331991209
},
"communicator.exchange": {
"total": 203.37748904799582,
"count": 18202,
"is_parallel": true,
"self": 203.37748904799582
},
"steps_from_proto": {
"total": 36.658298375001095,
"count": 18202,
"is_parallel": true,
"self": 6.754897070998254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.90340130400284,
"count": 182020,
"is_parallel": true,
"self": 29.90340130400284
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012665600002037536,
"count": 1,
"self": 0.00012665600002037536,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.849772465014,
"count": 438035,
"is_parallel": true,
"self": 10.14181078805916,
"children": {
"process_trajectory": {
"total": 259.2548983479559,
"count": 438035,
"is_parallel": true,
"self": 257.1967374069558,
"children": {
"RLTrainer._checkpoint": {
"total": 2.0581609410000965,
"count": 4,
"is_parallel": true,
"self": 2.0581609410000965
}
}
},
"_update_policy": {
"total": 206.45306332899895,
"count": 90,
"is_parallel": true,
"self": 82.4619810130016,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.99108231599735,
"count": 4584,
"is_parallel": true,
"self": 123.99108231599735
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14086209699996743,
"count": 1,
"self": 0.0008592979999093586,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14000279900005808,
"count": 1,
"self": 0.14000279900005808
}
}
}
}
}
}
}