kollis's picture
First Push
d24a5fd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.3838696479797363,
"min": 2.3838696479797363,
"max": 2.852088212966919,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 24150.984375,
"min": 24150.984375,
"max": 29239.607421875,
"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": 4.238966464996338,
"min": 0.4837804436683655,
"max": 4.238966464996338,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 822.3594970703125,
"min": 93.85340881347656,
"max": 822.3594970703125,
"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": 0.07191764903608618,
"min": 0.06578410346079253,
"max": 0.07402498377213143,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2876705961443447,
"min": 0.2667634130807082,
"max": 0.3701249188606572,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2919054653714685,
"min": 0.12397497212833854,
"max": 0.2919054653714685,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.167621861485874,
"min": 0.49589988851335415,
"max": 1.3578723143128786,
"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": 10.613636363636363,
"min": 3.5681818181818183,
"max": 10.613636363636363,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 467.0,
"min": 157.0,
"max": 518.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 10.613636363636363,
"min": 3.5681818181818183,
"max": 10.613636363636363,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 467.0,
"min": 157.0,
"max": 518.0,
"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": "1704187512",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704187636"
},
"total": 124.60185008100001,
"count": 1,
"self": 0.43392399700002215,
"children": {
"run_training.setup": {
"total": 0.0535794420000002,
"count": 1,
"self": 0.0535794420000002
},
"TrainerController.start_learning": {
"total": 124.11434664199999,
"count": 1,
"self": 0.15222619399912674,
"children": {
"TrainerController._reset_env": {
"total": 3.3155957490000105,
"count": 1,
"self": 3.3155957490000105
},
"TrainerController.advance": {
"total": 120.54410353900079,
"count": 4596,
"self": 0.07507929100245292,
"children": {
"env_step": {
"total": 120.46902424799833,
"count": 4596,
"self": 79.75593617999624,
"children": {
"SubprocessEnvManager._take_step": {
"total": 40.637967126001456,
"count": 4596,
"self": 0.3947150700030875,
"children": {
"TorchPolicy.evaluate": {
"total": 40.24325205599837,
"count": 4596,
"self": 40.24325205599837
}
}
},
"workers": {
"total": 0.07512094200063757,
"count": 4596,
"self": 0.0,
"children": {
"worker_root": {
"total": 123.74857979400173,
"count": 4596,
"is_parallel": true,
"self": 62.84004262000326,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004507263999983024,
"count": 1,
"is_parallel": true,
"self": 0.003088598000033471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014186659999495532,
"count": 10,
"is_parallel": true,
"self": 0.0014186659999495532
}
}
},
"UnityEnvironment.step": {
"total": 0.07089522499995837,
"count": 1,
"is_parallel": true,
"self": 0.0007547259999114431,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005386290000046756,
"count": 1,
"is_parallel": true,
"self": 0.0005386290000046756
},
"communicator.exchange": {
"total": 0.06747432200000958,
"count": 1,
"is_parallel": true,
"self": 0.06747432200000958
},
"steps_from_proto": {
"total": 0.002127548000032675,
"count": 1,
"is_parallel": true,
"self": 0.0004281170000695056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016994309999631696,
"count": 10,
"is_parallel": true,
"self": 0.0016994309999631696
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 60.90853717399847,
"count": 4595,
"is_parallel": true,
"self": 2.876464373998715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.443413275000978,
"count": 4595,
"is_parallel": true,
"self": 1.443413275000978
},
"communicator.exchange": {
"total": 47.18857699599715,
"count": 4595,
"is_parallel": true,
"self": 47.18857699599715
},
"steps_from_proto": {
"total": 9.400082529001622,
"count": 4595,
"is_parallel": true,
"self": 1.7683065549998673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.631775974001755,
"count": 45950,
"is_parallel": true,
"self": 7.631775974001755
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010626100004174077,
"count": 1,
"self": 0.00010626100004174077,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 118.9823660080155,
"count": 183923,
"is_parallel": true,
"self": 3.989067652022868,
"children": {
"process_trajectory": {
"total": 66.6986308049926,
"count": 183923,
"is_parallel": true,
"self": 66.56206042699262,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1365703779999876,
"count": 1,
"is_parallel": true,
"self": 0.1365703779999876
}
}
},
"_update_policy": {
"total": 48.29466755100003,
"count": 22,
"is_parallel": true,
"self": 16.629499025999735,
"children": {
"TorchPPOOptimizer.update": {
"total": 31.665168525000297,
"count": 1119,
"is_parallel": true,
"self": 31.665168525000297
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10231489900002089,
"count": 1,
"self": 0.0010375400000839363,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10127735899993695,
"count": 1,
"self": 0.10127735899993695
}
}
}
}
}
}
}