jakubgajski's picture
First Push
fd5926e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.6185333728790283,
"min": 1.6185333728790283,
"max": 2.3890488147735596,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 15685.20703125,
"min": 15685.20703125,
"max": 24492.52734375,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 499952.0,
"min": 209936.0,
"max": 499952.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 499952.0,
"min": 209936.0,
"max": 499952.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.35067081451416,
"min": 4.125368118286133,
"max": 10.35067081451416,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2111.536865234375,
"min": 792.0706787109375,
"max": 2111.536865234375,
"count": 30
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 0.41174212098121643,
"min": 0.29970523715019226,
"max": 0.41174212098121643,
"count": 30
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 83.99539184570312,
"min": 58.44252014160156,
"max": 83.99539184570312,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.2,
"min": 15.0,
"max": 24.2,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1331.0,
"min": 683.0,
"max": 1331.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.2,
"min": 15.0,
"max": 24.2,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1331.0,
"min": 683.0,
"max": 1331.0,
"count": 30
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 0.9702810207551176,
"min": 0.0,
"max": 0.9702810207551176,
"count": 30
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 53.36545614153147,
"min": 0.0,
"max": 53.36545614153147,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.14052760786062757,
"min": 0.13743979886894153,
"max": 0.14526880568945744,
"count": 17
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.14052760786062757,
"min": 0.13743979886894153,
"max": 0.14526880568945744,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.11250105779085841,
"min": 0.1080041357898523,
"max": 0.1483479710065183,
"count": 17
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.11250105779085841,
"min": 0.1080041357898523,
"max": 0.1483479710065183,
"count": 17
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.385697204799993e-06,
"min": 8.385697204799993e-06,
"max": 0.00016984804338399998,
"count": 17
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.385697204799993e-06,
"min": 8.385697204799993e-06,
"max": 0.00016984804338399998,
"count": 17
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1027952,
"min": 0.1027952,
"max": 0.15661600000000006,
"count": 17
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1027952,
"min": 0.1027952,
"max": 0.15661600000000006,
"count": 17
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014948047999999988,
"min": 0.00014948047999999988,
"max": 0.0028351384000000006,
"count": 17
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00014948047999999988,
"min": 0.00014948047999999988,
"max": 0.0028351384000000006,
"count": 17
},
"SnowballTarget.Losses.CuriosityForwardLoss.mean": {
"value": 0.04631114746370013,
"min": 0.03979384261582579,
"max": 0.05177491479153472,
"count": 17
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.04631114746370013,
"min": 0.03979384261582579,
"max": 0.05177491479153472,
"count": 17
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 1.4249065720845782,
"min": 1.4249065720845782,
"max": 2.0070621078733413,
"count": 17
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 1.4249065720845782,
"min": 1.4249065720845782,
"max": 2.0070621078733413,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683812710",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683813838"
},
"total": 1127.5446133629998,
"count": 1,
"self": 0.7297791769997275,
"children": {
"run_training.setup": {
"total": 0.039653480000197305,
"count": 1,
"self": 0.039653480000197305
},
"TrainerController.start_learning": {
"total": 1126.775180706,
"count": 1,
"self": 0.7847868159728932,
"children": {
"TrainerController._reset_env": {
"total": 3.5591430199997376,
"count": 1,
"self": 3.5591430199997376
},
"TrainerController.advance": {
"total": 1122.160470015027,
"count": 27287,
"self": 0.37183532803874186,
"children": {
"env_step": {
"total": 1121.7886346869882,
"count": 27287,
"self": 957.4939411440519,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.90950036098184,
"count": 27287,
"self": 2.7304017519550143,
"children": {
"TorchPolicy.evaluate": {
"total": 161.17909860902682,
"count": 27287,
"self": 161.17909860902682
}
}
},
"workers": {
"total": 0.3851931819544916,
"count": 27287,
"self": 0.0,
"children": {
"worker_root": {
"total": 1124.6364629710201,
"count": 27287,
"is_parallel": true,
"self": 766.363746886037,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019262570003775181,
"count": 1,
"is_parallel": true,
"self": 0.0006033180002305016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013229390001470165,
"count": 10,
"is_parallel": true,
"self": 0.0013229390001470165
}
}
},
"UnityEnvironment.step": {
"total": 0.03693232599971452,
"count": 1,
"is_parallel": true,
"self": 0.000581247999889456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000326738999774534,
"count": 1,
"is_parallel": true,
"self": 0.000326738999774534
},
"communicator.exchange": {
"total": 0.033779210000375315,
"count": 1,
"is_parallel": true,
"self": 0.033779210000375315
},
"steps_from_proto": {
"total": 0.0022451289996752166,
"count": 1,
"is_parallel": true,
"self": 0.0005249089990684297,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001720220000606787,
"count": 10,
"is_parallel": true,
"self": 0.001720220000606787
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 358.27271608498313,
"count": 27286,
"is_parallel": true,
"self": 14.223715283988895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.861399810001785,
"count": 27286,
"is_parallel": true,
"self": 7.861399810001785
},
"communicator.exchange": {
"total": 287.70915352500015,
"count": 27286,
"is_parallel": true,
"self": 287.70915352500015
},
"steps_from_proto": {
"total": 48.4784474659923,
"count": 27286,
"is_parallel": true,
"self": 9.105429239834848,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.373018226157456,
"count": 272860,
"is_parallel": true,
"self": 39.373018226157456
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.6364000354515156e-05,
"count": 1,
"self": 4.6364000354515156e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1115.195070694926,
"count": 794249,
"is_parallel": true,
"self": 18.099510688789906,
"children": {
"process_trajectory": {
"total": 515.2461097201353,
"count": 794249,
"is_parallel": true,
"self": 512.6004755141348,
"children": {
"RLTrainer._checkpoint": {
"total": 2.6456342060005227,
"count": 6,
"is_parallel": true,
"self": 2.6456342060005227
}
}
},
"_update_policy": {
"total": 581.8494502860008,
"count": 17,
"is_parallel": true,
"self": 303.6705323810138,
"children": {
"TorchPPOOptimizer.update": {
"total": 278.178917904987,
"count": 26799,
"is_parallel": true,
"self": 278.178917904987
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2707344909999847,
"count": 1,
"self": 0.0018728250001913693,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26886166599979333,
"count": 1,
"self": 0.26886166599979333
}
}
}
}
}
}
}