ammr's picture
addsnowballtarget
44c12c9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.379467248916626,
"min": 1.3658976554870605,
"max": 2.8902292251586914,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13338.0693359375,
"min": 13149.9287109375,
"max": 29806.396484375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.437034606933594,
"min": 0.36532363295555115,
"max": 8.467759132385254,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1729.592041015625,
"min": 70.87278747558594,
"max": 1729.592041015625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06762183531892815,
"min": 0.06283424676546608,
"max": 0.07704412460255243,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3381091765946408,
"min": 0.2513369870618643,
"max": 0.38522062301276216,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2600751572847366,
"min": 0.09842146840425867,
"max": 0.2953235766466926,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.3003757864236831,
"min": 0.39368587361703467,
"max": 1.4757395293782738,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0185898240000011e-07,
"min": 1.0185898240000011e-07,
"max": 9.891761082400001e-06,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.092949120000005e-07,
"min": 5.092949120000005e-07,
"max": 4.846881531200001e-05,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4999999999999999,
"min": 0.3999999999999999,
"max": 0.4999999999999999,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 16.654545454545456,
"min": 2.7954545454545454,
"max": 16.933333333333334,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 916.0,
"min": 123.0,
"max": 916.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 16.654545454545456,
"min": 2.7954545454545454,
"max": 16.933333333333334,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 916.0,
"min": 123.0,
"max": 916.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678036774",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678038129"
},
"total": 1355.2741498350001,
"count": 1,
"self": 0.42571783100038374,
"children": {
"run_training.setup": {
"total": 0.10620994700002484,
"count": 1,
"self": 0.10620994700002484
},
"TrainerController.start_learning": {
"total": 1354.7422220569997,
"count": 1,
"self": 1.2987555020931723,
"children": {
"TrainerController._reset_env": {
"total": 6.9214117719998285,
"count": 1,
"self": 6.9214117719998285
},
"TrainerController.advance": {
"total": 1346.3238731689066,
"count": 45481,
"self": 0.6902974328422715,
"children": {
"env_step": {
"total": 1345.6335757360644,
"count": 45481,
"self": 978.0263863250761,
"children": {
"SubprocessEnvManager._take_step": {
"total": 366.90428748296654,
"count": 45481,
"self": 3.8421440909337434,
"children": {
"TorchPolicy.evaluate": {
"total": 363.0621433920328,
"count": 45481,
"self": 81.0664011170361,
"children": {
"TorchPolicy.sample_actions": {
"total": 281.9957422749967,
"count": 45481,
"self": 281.9957422749967
}
}
}
}
},
"workers": {
"total": 0.7029019280216744,
"count": 45481,
"self": 0.0,
"children": {
"worker_root": {
"total": 1350.7219736509523,
"count": 45481,
"is_parallel": true,
"self": 745.7596506200007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002202131999638368,
"count": 1,
"is_parallel": true,
"self": 0.0007464009995601373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014557310000782309,
"count": 10,
"is_parallel": true,
"self": 0.0014557310000782309
}
}
},
"UnityEnvironment.step": {
"total": 0.12093137900001238,
"count": 1,
"is_parallel": true,
"self": 0.0005905819998588413,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003977070000473759,
"count": 1,
"is_parallel": true,
"self": 0.0003977070000473759
},
"communicator.exchange": {
"total": 0.11782462200017108,
"count": 1,
"is_parallel": true,
"self": 0.11782462200017108
},
"steps_from_proto": {
"total": 0.002118467999935092,
"count": 1,
"is_parallel": true,
"self": 0.0005638190000354371,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015546489998996549,
"count": 10,
"is_parallel": true,
"self": 0.0015546489998996549
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 604.9623230309517,
"count": 45480,
"is_parallel": true,
"self": 24.243029215894694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.017686898082047,
"count": 45480,
"is_parallel": true,
"self": 14.017686898082047
},
"communicator.exchange": {
"total": 484.74032751698724,
"count": 45480,
"is_parallel": true,
"self": 484.74032751698724
},
"steps_from_proto": {
"total": 81.96127939998769,
"count": 45480,
"is_parallel": true,
"self": 17.794618126076784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.1666612739109,
"count": 454800,
"is_parallel": true,
"self": 64.1666612739109
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.2113999825232895e-05,
"count": 1,
"self": 4.2113999825232895e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1337.9136293721012,
"count": 990341,
"is_parallel": true,
"self": 25.311831634034206,
"children": {
"process_trajectory": {
"total": 663.8091825050647,
"count": 990341,
"is_parallel": true,
"self": 659.3907684300657,
"children": {
"RLTrainer._checkpoint": {
"total": 4.418414074998964,
"count": 10,
"is_parallel": true,
"self": 4.418414074998964
}
}
},
"_update_policy": {
"total": 648.7926152330024,
"count": 227,
"is_parallel": true,
"self": 261.1463918159725,
"children": {
"TorchPPOOptimizer.update": {
"total": 387.6462234170299,
"count": 19290,
"is_parallel": true,
"self": 387.6462234170299
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19813950000025216,
"count": 1,
"self": 0.00316469400013375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1949748060001184,
"count": 1,
"self": 0.1949748060001184
}
}
}
}
}
}
}