npit's picture
baseline run
e57430c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.5710225105285645,
"min": 2.5710225105285645,
"max": 2.856943368911743,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 26103.591796875,
"min": 25062.275390625,
"max": 29320.80859375,
"count": 5
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 3.662187337875366,
"min": 0.477606862783432,
"max": 3.662187337875366,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 710.46435546875,
"min": 92.65573120117188,
"max": 710.46435546875,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06991415967429787,
"min": 0.06557775744746037,
"max": 0.0714941672523684,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2796566386971915,
"min": 0.27462112348353807,
"max": 0.357470836261842,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2818072118303355,
"min": 0.12357928893784537,
"max": 0.2818072118303355,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.127228847321342,
"min": 0.49431715575138147,
"max": 1.2221050975369472,
"count": 5
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.9928090024000003e-05,
"min": 2.9928090024000003e-05,
"max": 0.00026752801082399996,
"count": 5
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00011971236009600001,
"min": 0.00011971236009600001,
"max": 0.0010701120432959998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10997600000000002,
"min": 0.10997600000000002,
"max": 0.18917599999999998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4399040000000001,
"min": 0.4399040000000001,
"max": 0.8468800000000001,
"count": 5
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0005078024,
"min": 0.0005078024,
"max": 0.0044598824,
"count": 5
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0020312096,
"min": 0.0020312096,
"max": 0.0178395296,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 9.318181818181818,
"min": 3.1818181818181817,
"max": 9.318181818181818,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 410.0,
"min": 140.0,
"max": 431.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 9.318181818181818,
"min": 3.1818181818181817,
"max": 9.318181818181818,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 410.0,
"min": 140.0,
"max": 431.0,
"count": 5
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677704789",
"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",
"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": "1677704928"
},
"total": 138.78058630199985,
"count": 1,
"self": 0.4396696079998037,
"children": {
"run_training.setup": {
"total": 0.12163142700001117,
"count": 1,
"self": 0.12163142700001117
},
"TrainerController.start_learning": {
"total": 138.21928526700003,
"count": 1,
"self": 0.20075411599896142,
"children": {
"TrainerController._reset_env": {
"total": 10.30869804300005,
"count": 1,
"self": 10.30869804300005
},
"TrainerController.advance": {
"total": 127.57200488400099,
"count": 4599,
"self": 0.0799404970091473,
"children": {
"env_step": {
"total": 127.49206438699184,
"count": 4599,
"self": 88.55169160800597,
"children": {
"SubprocessEnvManager._take_step": {
"total": 38.86204588198484,
"count": 4599,
"self": 0.43308382398936374,
"children": {
"TorchPolicy.evaluate": {
"total": 38.42896205799548,
"count": 4599,
"self": 8.373703964994093,
"children": {
"TorchPolicy.sample_actions": {
"total": 30.055258093001385,
"count": 4599,
"self": 30.055258093001385
}
}
}
}
},
"workers": {
"total": 0.07832689700103401,
"count": 4599,
"self": 0.0,
"children": {
"worker_root": {
"total": 137.71994141200548,
"count": 4599,
"is_parallel": true,
"self": 70.52911878300301,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00889095799993811,
"count": 1,
"is_parallel": true,
"self": 0.003923497999949177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004967459999988932,
"count": 10,
"is_parallel": true,
"self": 0.004967459999988932
}
}
},
"UnityEnvironment.step": {
"total": 0.050089856000113286,
"count": 1,
"is_parallel": true,
"self": 0.0005253100000572886,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003847069999665109,
"count": 1,
"is_parallel": true,
"self": 0.0003847069999665109
},
"communicator.exchange": {
"total": 0.04704924399993615,
"count": 1,
"is_parallel": true,
"self": 0.04704924399993615
},
"steps_from_proto": {
"total": 0.0021305950001533347,
"count": 1,
"is_parallel": true,
"self": 0.0004836670002532628,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016469279999000719,
"count": 10,
"is_parallel": true,
"self": 0.0016469279999000719
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 67.19082262900247,
"count": 4598,
"is_parallel": true,
"self": 2.7024671300014234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.5489829850009755,
"count": 4598,
"is_parallel": true,
"self": 1.5489829850009755
},
"communicator.exchange": {
"total": 53.79857235399527,
"count": 4598,
"is_parallel": true,
"self": 53.79857235399527
},
"steps_from_proto": {
"total": 9.140800160004801,
"count": 4598,
"is_parallel": true,
"self": 2.079217898036859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.061582261967942,
"count": 45980,
"is_parallel": true,
"self": 7.061582261967942
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000327192999975523,
"count": 1,
"self": 0.000327192999975523,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 126.59938873405531,
"count": 114305,
"is_parallel": true,
"self": 3.007353538071584,
"children": {
"process_trajectory": {
"total": 74.28110760698382,
"count": 114305,
"is_parallel": true,
"self": 72.4521893359838,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8289182710000205,
"count": 5,
"is_parallel": true,
"self": 1.8289182710000205
}
}
},
"_update_policy": {
"total": 49.3109275889999,
"count": 22,
"is_parallel": true,
"self": 18.230926510004792,
"children": {
"TorchPPOOptimizer.update": {
"total": 31.08000107899511,
"count": 1119,
"is_parallel": true,
"self": 31.08000107899511
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13750103100005617,
"count": 1,
"self": 0.000981951000085246,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13651907999997093,
"count": 1,
"self": 0.13651907999997093
}
}
}
}
}
}
}