sunxysun's picture
First Push
23e65b1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7917704582214355,
"min": 0.7917704582214355,
"max": 2.8447000980377197,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7524.986328125,
"min": 7524.986328125,
"max": 29038.69921875,
"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": 13.237391471862793,
"min": 0.4014391601085663,
"max": 13.237391471862793,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2581.291259765625,
"min": 77.87919616699219,
"max": 2684.99072265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06988332155485884,
"min": 0.061607838289666116,
"max": 0.07516808249933735,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27953328621943535,
"min": 0.2506051252564123,
"max": 0.362789912058004,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20957181588107462,
"min": 0.12068815172910143,
"max": 0.307986620126986,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8382872635242985,
"min": 0.4827526069164057,
"max": 1.5399331006349302,
"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": 25.954545454545453,
"min": 3.409090909090909,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 150.0,
"max": 1436.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.409090909090909,
"max": 26.10909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 150.0,
"max": 1436.0,
"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": "1754529681",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1754530101"
},
"total": 420.2900327010001,
"count": 1,
"self": 0.4272181480001791,
"children": {
"run_training.setup": {
"total": 0.024545895999949607,
"count": 1,
"self": 0.024545895999949607
},
"TrainerController.start_learning": {
"total": 419.83826865699996,
"count": 1,
"self": 0.32617718599908585,
"children": {
"TrainerController._reset_env": {
"total": 3.1015302449999353,
"count": 1,
"self": 3.1015302449999353
},
"TrainerController.advance": {
"total": 416.31047800600095,
"count": 18192,
"self": 0.36014061599712477,
"children": {
"env_step": {
"total": 298.4049976589939,
"count": 18192,
"self": 230.0941275770199,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.10750211098173,
"count": 18192,
"self": 1.245896246997063,
"children": {
"TorchPolicy.evaluate": {
"total": 66.86160586398466,
"count": 18192,
"self": 66.86160586398466
}
}
},
"workers": {
"total": 0.20336797099230353,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 418.4386820069965,
"count": 18192,
"is_parallel": true,
"self": 216.24021979200984,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004980611999940265,
"count": 1,
"is_parallel": true,
"self": 0.0035599739996996504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001420638000240615,
"count": 10,
"is_parallel": true,
"self": 0.001420638000240615
}
}
},
"UnityEnvironment.step": {
"total": 0.07923897699993177,
"count": 1,
"is_parallel": true,
"self": 0.0006078249999745822,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000406531999942672,
"count": 1,
"is_parallel": true,
"self": 0.000406531999942672
},
"communicator.exchange": {
"total": 0.07633220200000324,
"count": 1,
"is_parallel": true,
"self": 0.07633220200000324
},
"steps_from_proto": {
"total": 0.0018924180000112756,
"count": 1,
"is_parallel": true,
"self": 0.0004151919999912934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014772260000199822,
"count": 10,
"is_parallel": true,
"self": 0.0014772260000199822
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.19846221498665,
"count": 18191,
"is_parallel": true,
"self": 9.750826955980301,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.301893614997198,
"count": 18191,
"is_parallel": true,
"self": 5.301893614997198
},
"communicator.exchange": {
"total": 155.64922888299816,
"count": 18191,
"is_parallel": true,
"self": 155.64922888299816
},
"steps_from_proto": {
"total": 31.49651276101099,
"count": 18191,
"is_parallel": true,
"self": 5.540960155017615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.955552605993375,
"count": 181910,
"is_parallel": true,
"self": 25.955552605993375
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.5453397310099,
"count": 18192,
"self": 0.41902085600418104,
"children": {
"process_trajectory": {
"total": 26.779774331006593,
"count": 18192,
"self": 26.369181739006535,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41059259200005727,
"count": 4,
"self": 0.41059259200005727
}
}
},
"_update_policy": {
"total": 90.34654454399913,
"count": 90,
"self": 37.07054394900024,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.27600059499889,
"count": 4587,
"self": 53.27600059499889
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1639999684120994e-06,
"count": 1,
"self": 1.1639999684120994e-06
},
"TrainerController._save_models": {
"total": 0.10008205600001929,
"count": 1,
"self": 0.0012071639998794126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09887489200013988,
"count": 1,
"self": 0.09887489200013988
}
}
}
}
}
}
}