polyconnect's picture
Locally trained
9a118f8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8751007914543152,
"min": 0.8751007914543152,
"max": 2.851548910140991,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8393.966796875,
"min": 8393.966796875,
"max": 29296.8125,
"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": 12.883551597595215,
"min": 0.3710114657878876,
"max": 12.933782577514648,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2512.29248046875,
"min": 71.97622680664062,
"max": 2638.49169921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0667367311667191,
"min": 0.06220210300131892,
"max": 0.07385022185831878,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2669469246668764,
"min": 0.25486488775099064,
"max": 0.3435277895677798,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18553577195487772,
"min": 0.12687591150832161,
"max": 0.27973537935930143,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7421430878195109,
"min": 0.5075036460332865,
"max": 1.398676896796507,
"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": 25.227272727272727,
"min": 3.5454545454545454,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 156.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.5454545454545454,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 156.0,
"max": 1406.0,
"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": "1718381420",
"python_version": "3.10.14 (main, Jun 14 2024, 18:23:26) [GCC 11.4.0]",
"command_line_arguments": "/home/ivan/.env/hf310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718381686"
},
"total": 266.73982527601765,
"count": 1,
"self": 0.2217029849998653,
"children": {
"run_training.setup": {
"total": 0.01772404502844438,
"count": 1,
"self": 0.01772404502844438
},
"TrainerController.start_learning": {
"total": 266.50039824598935,
"count": 1,
"self": 0.36665289383381605,
"children": {
"TrainerController._reset_env": {
"total": 1.0074500190094113,
"count": 1,
"self": 1.0074500190094113
},
"TrainerController.advance": {
"total": 265.04363459616434,
"count": 18206,
"self": 0.18115055077942088,
"children": {
"env_step": {
"total": 264.8624840453849,
"count": 18206,
"self": 183.88318983098725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.78306001168676,
"count": 18206,
"self": 0.8253579681040719,
"children": {
"TorchPolicy.evaluate": {
"total": 79.95770204358269,
"count": 18206,
"self": 79.95770204358269
}
}
},
"workers": {
"total": 0.19623420271091163,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 266.04770171339624,
"count": 18206,
"is_parallel": true,
"self": 130.5107266350533,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011995669919997454,
"count": 1,
"is_parallel": true,
"self": 0.0003199088969267905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008796580950729549,
"count": 10,
"is_parallel": true,
"self": 0.0008796580950729549
}
}
},
"UnityEnvironment.step": {
"total": 0.020269825006835163,
"count": 1,
"is_parallel": true,
"self": 0.00022742105647921562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003777029924094677,
"count": 1,
"is_parallel": true,
"self": 0.0003777029924094677
},
"communicator.exchange": {
"total": 0.01894824398914352,
"count": 1,
"is_parallel": true,
"self": 0.01894824398914352
},
"steps_from_proto": {
"total": 0.0007164569688029587,
"count": 1,
"is_parallel": true,
"self": 0.00016149604925885797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005549609195441008,
"count": 10,
"is_parallel": true,
"self": 0.0005549609195441008
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 135.53697507834295,
"count": 18205,
"is_parallel": true,
"self": 7.385933380981442,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.248280268686358,
"count": 18205,
"is_parallel": true,
"self": 3.248280268686358
},
"communicator.exchange": {
"total": 104.01748923194828,
"count": 18205,
"is_parallel": true,
"self": 104.01748923194828
},
"steps_from_proto": {
"total": 20.885272196726874,
"count": 18205,
"is_parallel": true,
"self": 3.612728105217684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.27254409150919,
"count": 182050,
"is_parallel": true,
"self": 17.27254409150919
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.50789768062532e-05,
"count": 1,
"self": 7.50789768062532e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 264.6353142752778,
"count": 167784,
"is_parallel": true,
"self": 1.8442222691955976,
"children": {
"process_trajectory": {
"total": 152.74305728869513,
"count": 167784,
"is_parallel": true,
"self": 152.3370479856385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.40600930305663496,
"count": 4,
"is_parallel": true,
"self": 0.40600930305663496
}
}
},
"_update_policy": {
"total": 110.04803471738705,
"count": 90,
"is_parallel": true,
"self": 27.158907177159563,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.88912754022749,
"count": 4584,
"is_parallel": true,
"self": 82.88912754022749
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08258565800497308,
"count": 1,
"self": 0.0004328389768488705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08215281902812421,
"count": 1,
"self": 0.08215281902812421
}
}
}
}
}
}
}