dor88's picture
first try - vanilla
7e87142
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9189017415046692,
"min": 0.9154658317565918,
"max": 2.862773895263672,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8773.673828125,
"min": 8773.673828125,
"max": 29317.66796875,
"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": 12.951765060424805,
"min": 0.42400386929512024,
"max": 12.963489532470703,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.59423828125,
"min": 82.25675201416016,
"max": 2648.400390625,
"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": 0.0719765107658389,
"min": 0.06232592628460706,
"max": 0.07769479124865886,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2879060430633556,
"min": 0.25704346219515406,
"max": 0.36494574334538615,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19111960257093114,
"min": 0.11470029978355503,
"max": 0.3003060784410028,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7644784102837245,
"min": 0.45880119913422013,
"max": 1.501530392205014,
"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": 25.568181818181817,
"min": 3.2954545454545454,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 145.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.2954545454545454,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 145.0,
"max": 1406.0,
"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": "1677520990",
"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": "1677521472"
},
"total": 481.46590115999993,
"count": 1,
"self": 0.4386650509999299,
"children": {
"run_training.setup": {
"total": 0.11590165400002661,
"count": 1,
"self": 0.11590165400002661
},
"TrainerController.start_learning": {
"total": 480.911334455,
"count": 1,
"self": 0.5922681579817208,
"children": {
"TrainerController._reset_env": {
"total": 9.942966959000046,
"count": 1,
"self": 9.942966959000046
},
"TrainerController.advance": {
"total": 470.25125177101825,
"count": 18203,
"self": 0.3202453090068502,
"children": {
"env_step": {
"total": 469.9310064620114,
"count": 18203,
"self": 323.67430929803163,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.9540273679935,
"count": 18203,
"self": 1.6100914679976768,
"children": {
"TorchPolicy.evaluate": {
"total": 144.3439358999958,
"count": 18203,
"self": 32.676737654006615,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.6671982459892,
"count": 18203,
"self": 111.6671982459892
}
}
}
}
},
"workers": {
"total": 0.30266979598627586,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 479.0963606460108,
"count": 18203,
"is_parallel": true,
"self": 230.31774738999536,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008913016999940737,
"count": 1,
"is_parallel": true,
"self": 0.004889057999662327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00402395900027841,
"count": 10,
"is_parallel": true,
"self": 0.00402395900027841
}
}
},
"UnityEnvironment.step": {
"total": 0.09469672700004139,
"count": 1,
"is_parallel": true,
"self": 0.0005673240001442537,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037564399997336295,
"count": 1,
"is_parallel": true,
"self": 0.00037564399997336295
},
"communicator.exchange": {
"total": 0.0920923489999268,
"count": 1,
"is_parallel": true,
"self": 0.0920923489999268
},
"steps_from_proto": {
"total": 0.0016614099999969767,
"count": 1,
"is_parallel": true,
"self": 0.0004061150000325142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012552949999644625,
"count": 10,
"is_parallel": true,
"self": 0.0012552949999644625
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.77861325601543,
"count": 18202,
"is_parallel": true,
"self": 9.980411924992382,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.595009095003888,
"count": 18202,
"is_parallel": true,
"self": 5.595009095003888
},
"communicator.exchange": {
"total": 199.7740571730094,
"count": 18202,
"is_parallel": true,
"self": 199.7740571730094
},
"steps_from_proto": {
"total": 33.42913506300977,
"count": 18202,
"is_parallel": true,
"self": 7.601306684984365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.8278283780254,
"count": 182020,
"is_parallel": true,
"self": 25.8278283780254
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012467300007301674,
"count": 1,
"self": 0.00012467300007301674,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 466.360406021858,
"count": 429578,
"is_parallel": true,
"self": 11.197337166819807,
"children": {
"process_trajectory": {
"total": 268.7988572310385,
"count": 429578,
"is_parallel": true,
"self": 267.66729642803864,
"children": {
"RLTrainer._checkpoint": {
"total": 1.131560802999843,
"count": 4,
"is_parallel": true,
"self": 1.131560802999843
}
}
},
"_update_policy": {
"total": 186.36421162399972,
"count": 90,
"is_parallel": true,
"self": 65.39949964199866,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.96471198200106,
"count": 4584,
"is_parallel": true,
"self": 120.96471198200106
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12472289399988767,
"count": 1,
"self": 0.0013160099999822705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1234068839999054,
"count": 1,
"self": 0.1234068839999054
}
}
}
}
}
}
}