Icarus013's picture
First Push
bad0f38 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8999742865562439,
"min": 0.868094801902771,
"max": 2.862891674041748,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8553.35546875,
"min": 8553.35546875,
"max": 29224.3984375,
"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": 12.900633811950684,
"min": 0.5405790209770203,
"max": 12.900633811950684,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.62353515625,
"min": 104.87232971191406,
"max": 2599.439453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06937841421104703,
"min": 0.061486044758067675,
"max": 0.07390720671563245,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2775136568441881,
"min": 0.2459441790322707,
"max": 0.3695360335781622,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19189216057751696,
"min": 0.13061792440666797,
"max": 0.2675466817968032,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7675686423100678,
"min": 0.5224716976266719,
"max": 1.321916317530707,
"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": 25.65909090909091,
"min": 3.5,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 154.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.5,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 154.0,
"max": 1409.0,
"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": "1748527777",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748528273"
},
"total": 495.8393523220001,
"count": 1,
"self": 0.48816068800010726,
"children": {
"run_training.setup": {
"total": 0.024611046000018177,
"count": 1,
"self": 0.024611046000018177
},
"TrainerController.start_learning": {
"total": 495.32658058799996,
"count": 1,
"self": 0.47585461800451867,
"children": {
"TrainerController._reset_env": {
"total": 3.6401534919999676,
"count": 1,
"self": 3.6401534919999676
},
"TrainerController.advance": {
"total": 491.11588257099527,
"count": 18192,
"self": 0.4948300859966821,
"children": {
"env_step": {
"total": 355.41751918099953,
"count": 18192,
"self": 271.8753121409761,
"children": {
"SubprocessEnvManager._take_step": {
"total": 83.26267561401141,
"count": 18192,
"self": 1.5213795900244804,
"children": {
"TorchPolicy.evaluate": {
"total": 81.74129602398693,
"count": 18192,
"self": 81.74129602398693
}
}
},
"workers": {
"total": 0.27953142601199943,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.690293610995,
"count": 18192,
"is_parallel": true,
"self": 256.200182503993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0068851029999450475,
"count": 1,
"is_parallel": true,
"self": 0.005314418999773807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015706840001712408,
"count": 10,
"is_parallel": true,
"self": 0.0015706840001712408
}
}
},
"UnityEnvironment.step": {
"total": 0.04082305300005373,
"count": 1,
"is_parallel": true,
"self": 0.0006748789999164728,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004181770000286633,
"count": 1,
"is_parallel": true,
"self": 0.0004181770000286633
},
"communicator.exchange": {
"total": 0.037514252000050874,
"count": 1,
"is_parallel": true,
"self": 0.037514252000050874
},
"steps_from_proto": {
"total": 0.002215745000057723,
"count": 1,
"is_parallel": true,
"self": 0.0006085810001650316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016071639998926912,
"count": 10,
"is_parallel": true,
"self": 0.0016071639998926912
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.490111107002,
"count": 18191,
"is_parallel": true,
"self": 11.039873492991205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.3787251740078545,
"count": 18191,
"is_parallel": true,
"self": 6.3787251740078545
},
"communicator.exchange": {
"total": 182.75269816300306,
"count": 18191,
"is_parallel": true,
"self": 182.75269816300306
},
"steps_from_proto": {
"total": 37.31881427699989,
"count": 18191,
"is_parallel": true,
"self": 6.961247909987833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.357566367012055,
"count": 181910,
"is_parallel": true,
"self": 30.357566367012055
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 135.20353330399905,
"count": 18192,
"self": 0.630565780998154,
"children": {
"process_trajectory": {
"total": 31.40549766700167,
"count": 18192,
"self": 30.93867408400172,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4668235829999503,
"count": 4,
"self": 0.4668235829999503
}
}
},
"_update_policy": {
"total": 103.16746985599923,
"count": 90,
"self": 42.59937217000197,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.56809768599726,
"count": 4587,
"self": 60.56809768599726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.500001058564521e-07,
"count": 1,
"self": 8.500001058564521e-07
},
"TrainerController._save_models": {
"total": 0.094689057000096,
"count": 1,
"self": 0.0010079640001094958,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0936810929999865,
"count": 1,
"self": 0.0936810929999865
}
}
}
}
}
}
}