danlindb's picture
First Push
67eb00e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7458433508872986,
"min": 0.7458433508872986,
"max": 2.851247549057007,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7129.5166015625,
"min": 7129.5166015625,
"max": 29199.625,
"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": 12.949211120605469,
"min": 0.35189902782440186,
"max": 12.949211120605469,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.09619140625,
"min": 68.2684097290039,
"max": 2630.973388671875,
"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": 0.07412076777037845,
"min": 0.06254649786712309,
"max": 0.07599031007132498,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2964830710815138,
"min": 0.25018599146849235,
"max": 0.37021328762428174,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1838383601576674,
"min": 0.12520527021101147,
"max": 0.2813601681560862,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7353534406306697,
"min": 0.5008210808440459,
"max": 1.37109034364203,
"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": 25.613636363636363,
"min": 3.340909090909091,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 147.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.340909090909091,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 147.0,
"max": 1399.0,
"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": "1702484332",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702484796"
},
"total": 464.139812096,
"count": 1,
"self": 0.3963249360001555,
"children": {
"run_training.setup": {
"total": 0.05743971399988368,
"count": 1,
"self": 0.05743971399988368
},
"TrainerController.start_learning": {
"total": 463.686047446,
"count": 1,
"self": 0.534101134007642,
"children": {
"TrainerController._reset_env": {
"total": 3.4895418620001237,
"count": 1,
"self": 3.4895418620001237
},
"TrainerController.advance": {
"total": 459.5798967959922,
"count": 18200,
"self": 0.24208216998954413,
"children": {
"env_step": {
"total": 459.3378146260027,
"count": 18200,
"self": 309.5652086099642,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.50459805700848,
"count": 18200,
"self": 1.4255168110164504,
"children": {
"TorchPolicy.evaluate": {
"total": 148.07908124599203,
"count": 18200,
"self": 148.07908124599203
}
}
},
"workers": {
"total": 0.2680079590300011,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.46112455499633,
"count": 18200,
"is_parallel": true,
"self": 226.39337827998452,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005849501000056989,
"count": 1,
"is_parallel": true,
"self": 0.004349954000417711,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014995469996392785,
"count": 10,
"is_parallel": true,
"self": 0.0014995469996392785
}
}
},
"UnityEnvironment.step": {
"total": 0.06631763099994714,
"count": 1,
"is_parallel": true,
"self": 0.0006381829998645117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004077240000697202,
"count": 1,
"is_parallel": true,
"self": 0.0004077240000697202
},
"communicator.exchange": {
"total": 0.06308065400003215,
"count": 1,
"is_parallel": true,
"self": 0.06308065400003215
},
"steps_from_proto": {
"total": 0.002191069999980755,
"count": 1,
"is_parallel": true,
"self": 0.0004112899998744979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001779780000106257,
"count": 10,
"is_parallel": true,
"self": 0.001779780000106257
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.0677462750118,
"count": 18199,
"is_parallel": true,
"self": 10.292298843038907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.209216072992831,
"count": 18199,
"is_parallel": true,
"self": 5.209216072992831
},
"communicator.exchange": {
"total": 187.63434296999844,
"count": 18199,
"is_parallel": true,
"self": 187.63434296999844
},
"steps_from_proto": {
"total": 32.93188838898163,
"count": 18199,
"is_parallel": true,
"self": 5.987762734974012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.94412565400762,
"count": 181990,
"is_parallel": true,
"self": 26.94412565400762
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001543519999813725,
"count": 1,
"self": 0.0001543519999813725,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 455.69286197496695,
"count": 492201,
"is_parallel": true,
"self": 10.415621067984603,
"children": {
"process_trajectory": {
"total": 258.20918903398183,
"count": 492201,
"is_parallel": true,
"self": 257.5637758459818,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6454131880000205,
"count": 4,
"is_parallel": true,
"self": 0.6454131880000205
}
}
},
"_update_policy": {
"total": 187.0680518730005,
"count": 90,
"is_parallel": true,
"self": 56.68951503301059,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.37853683998992,
"count": 4584,
"is_parallel": true,
"self": 130.37853683998992
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08235330200000135,
"count": 1,
"self": 0.0008569389999593113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08149636300004204,
"count": 1,
"self": 0.08149636300004204
}
}
}
}
}
}
}