Ithai's picture
Second training of SnowballTarget
b9f671a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.7821705341339111,
"min": 1.7821705341339111,
"max": 2.8731801509857178,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 18290.416015625,
"min": 17477.40234375,
"max": 29392.6328125,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.736564636230469,
"min": 0.3118304908275604,
"max": 8.736564636230469,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1782.25927734375,
"min": 60.4951171875,
"max": 1782.25927734375,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06863421420600976,
"min": 0.06392189127612202,
"max": 0.07024109168879816,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.34317107103004885,
"min": 0.2556875651044881,
"max": 0.3512054584439908,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.28663327203077427,
"min": 0.10991966960878641,
"max": 0.29535610751778474,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.4331663601538713,
"min": 0.43967867843514563,
"max": 1.4767805375889236,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.963636363636365,
"min": 3.2954545454545454,
"max": 18.963636363636365,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1043.0,
"min": 145.0,
"max": 1043.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.963636363636365,
"min": 3.2954545454545454,
"max": 18.963636363636365,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1043.0,
"min": 145.0,
"max": 1043.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676560222",
"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=SnowballTarget2 --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": "1.21.6",
"end_time_seconds": "1676560538"
},
"total": 316.566263928,
"count": 1,
"self": 0.7044892200001414,
"children": {
"run_training.setup": {
"total": 0.2800859509999327,
"count": 1,
"self": 0.2800859509999327
},
"TrainerController.start_learning": {
"total": 315.58168875699994,
"count": 1,
"self": 0.5410299970035339,
"children": {
"TrainerController._reset_env": {
"total": 4.793922606000024,
"count": 1,
"self": 4.793922606000024
},
"TrainerController.advance": {
"total": 310.10606949999624,
"count": 9133,
"self": 0.26073751999683736,
"children": {
"env_step": {
"total": 309.8453319799994,
"count": 9133,
"self": 240.82880374899605,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.78319246600199,
"count": 9133,
"self": 1.3243745520061339,
"children": {
"TorchPolicy.evaluate": {
"total": 67.45881791399586,
"count": 9133,
"self": 11.197451452998166,
"children": {
"TorchPolicy.sample_actions": {
"total": 56.26136646099769,
"count": 9133,
"self": 56.26136646099769
}
}
}
}
},
"workers": {
"total": 0.23333576500135678,
"count": 9133,
"self": 0.0,
"children": {
"worker_root": {
"total": 314.4614089960039,
"count": 9133,
"is_parallel": true,
"self": 140.36517281599595,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004462665000005472,
"count": 1,
"is_parallel": true,
"self": 0.0019633170001043254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002499347999901147,
"count": 10,
"is_parallel": true,
"self": 0.002499347999901147
}
}
},
"UnityEnvironment.step": {
"total": 0.06726798199997575,
"count": 1,
"is_parallel": true,
"self": 0.0007433199998558848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004140890000599029,
"count": 1,
"is_parallel": true,
"self": 0.0004140890000599029
},
"communicator.exchange": {
"total": 0.06349068600002283,
"count": 1,
"is_parallel": true,
"self": 0.06349068600002283
},
"steps_from_proto": {
"total": 0.0026198870000371244,
"count": 1,
"is_parallel": true,
"self": 0.000612830999898506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020070560001386184,
"count": 10,
"is_parallel": true,
"self": 0.0020070560001386184
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 174.09623618000796,
"count": 9132,
"is_parallel": true,
"self": 7.351983980000568,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.026871084005052,
"count": 9132,
"is_parallel": true,
"self": 4.026871084005052
},
"communicator.exchange": {
"total": 138.6437173779991,
"count": 9132,
"is_parallel": true,
"self": 138.6437173779991
},
"steps_from_proto": {
"total": 24.073663738003233,
"count": 9132,
"is_parallel": true,
"self": 5.545508122019555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.528155615983678,
"count": 91320,
"is_parallel": true,
"self": 18.528155615983678
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00039272000003620633,
"count": 1,
"self": 0.00039272000003620633,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 306.7726144169992,
"count": 366654,
"is_parallel": true,
"self": 10.093939900961459,
"children": {
"process_trajectory": {
"total": 170.36094030203787,
"count": 366654,
"is_parallel": true,
"self": 168.24968849803759,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1112518040002897,
"count": 10,
"is_parallel": true,
"self": 2.1112518040002897
}
}
},
"_update_policy": {
"total": 126.31773421399987,
"count": 45,
"is_parallel": true,
"self": 44.44094689799829,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.87678731600158,
"count": 2292,
"is_parallel": true,
"self": 81.87678731600158
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14027393400010624,
"count": 1,
"self": 0.001327712000147585,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13894622199995865,
"count": 1,
"self": 0.13894622199995865
}
}
}
}
}
}
}