vicha-w's picture
First Push
4c36933 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9207598567008972,
"min": 0.9207598567008972,
"max": 2.873241901397705,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8791.4150390625,
"min": 8791.4150390625,
"max": 29393.265625,
"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": 12.842485427856445,
"min": 0.4010412096977234,
"max": 12.842485427856445,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.28466796875,
"min": 77.80199432373047,
"max": 2603.43115234375,
"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": 0.0622824452824288,
"min": 0.0622824452824288,
"max": 0.07444484871670924,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2491297811297152,
"min": 0.2491297811297152,
"max": 0.3722242435835462,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1943443817104779,
"min": 0.11837491384186946,
"max": 0.2792486208911035,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7773775268419116,
"min": 0.47349965536747785,
"max": 1.3962431044555177,
"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": 25.25,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 142.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 3.227272727272727,
"max": 25.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 142.0,
"max": 1393.0,
"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": "1714327528",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714328039"
},
"total": 511.01607386299975,
"count": 1,
"self": 0.43385825899940755,
"children": {
"run_training.setup": {
"total": 0.0739678240001922,
"count": 1,
"self": 0.0739678240001922
},
"TrainerController.start_learning": {
"total": 510.50824778000015,
"count": 1,
"self": 0.7068501850126268,
"children": {
"TrainerController._reset_env": {
"total": 2.378280650000306,
"count": 1,
"self": 2.378280650000306
},
"TrainerController.advance": {
"total": 507.3261577959879,
"count": 18199,
"self": 0.34882766694863676,
"children": {
"env_step": {
"total": 506.9773301290393,
"count": 18199,
"self": 333.16157579404535,
"children": {
"SubprocessEnvManager._take_step": {
"total": 173.45148085501523,
"count": 18199,
"self": 1.742721879984856,
"children": {
"TorchPolicy.evaluate": {
"total": 171.70875897503038,
"count": 18199,
"self": 171.70875897503038
}
}
},
"workers": {
"total": 0.3642734799786922,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 509.0704450930243,
"count": 18199,
"is_parallel": true,
"self": 250.1866961530386,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031772570000612177,
"count": 1,
"is_parallel": true,
"self": 0.0008161969999491703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023610600001120474,
"count": 10,
"is_parallel": true,
"self": 0.0023610600001120474
}
}
},
"UnityEnvironment.step": {
"total": 0.037808722000136186,
"count": 1,
"is_parallel": true,
"self": 0.000684514000568015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004164229999332747,
"count": 1,
"is_parallel": true,
"self": 0.0004164229999332747
},
"communicator.exchange": {
"total": 0.03447962499967616,
"count": 1,
"is_parallel": true,
"self": 0.03447962499967616
},
"steps_from_proto": {
"total": 0.0022281599999587343,
"count": 1,
"is_parallel": true,
"self": 0.0005451120000543597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016830479999043746,
"count": 10,
"is_parallel": true,
"self": 0.0016830479999043746
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 258.8837489399857,
"count": 18198,
"is_parallel": true,
"self": 11.4542391559512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.2090396690259695,
"count": 18198,
"is_parallel": true,
"self": 6.2090396690259695
},
"communicator.exchange": {
"total": 202.73592699603023,
"count": 18198,
"is_parallel": true,
"self": 202.73592699603023
},
"steps_from_proto": {
"total": 38.48454311897831,
"count": 18198,
"is_parallel": true,
"self": 7.540658323970092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.943884795008216,
"count": 181980,
"is_parallel": true,
"self": 30.943884795008216
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015591199962727842,
"count": 1,
"self": 0.00015591199962727842,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 500.8392818950683,
"count": 757233,
"is_parallel": true,
"self": 16.482818886145196,
"children": {
"process_trajectory": {
"total": 279.3807827549249,
"count": 757233,
"is_parallel": true,
"self": 278.3456094039252,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0351733509996848,
"count": 4,
"is_parallel": true,
"self": 1.0351733509996848
}
}
},
"_update_policy": {
"total": 204.97568025399823,
"count": 90,
"is_parallel": true,
"self": 56.57653398299908,
"children": {
"TorchPPOOptimizer.update": {
"total": 148.39914627099915,
"count": 4584,
"is_parallel": true,
"self": 148.39914627099915
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0968032369996763,
"count": 1,
"self": 0.0012513619999481307,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09555187499972817,
"count": 1,
"self": 0.09555187499972817
}
}
}
}
}
}
}