GesturingMan's picture
First model push
27cf377
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7111499309539795,
"min": 0.6551768779754639,
"max": 2.8717041015625,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6868.2861328125,
"min": 6271.01416015625,
"max": 29630.2421875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.704948425292969,
"min": 0.31980055570602417,
"max": 13.747077941894531,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2809.514404296875,
"min": 62.04130554199219,
"max": 2809.514404296875,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06720404608172877,
"min": 0.06186729680805858,
"max": 0.08012354715092264,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3360202304086438,
"min": 0.24746918723223432,
"max": 0.3900562848755405,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1756350955250216,
"min": 0.10825744776201306,
"max": 0.273548203940485,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8781754776251081,
"min": 0.4330297910480522,
"max": 1.2923669452760733,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.509090909090908,
"min": 3.090909090909091,
"max": 27.363636363636363,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1458.0,
"min": 136.0,
"max": 1493.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.509090909090908,
"min": 3.090909090909091,
"max": 27.363636363636363,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1458.0,
"min": 136.0,
"max": 1493.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676286401",
"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=SnowballTarget3 --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": "1676287519"
},
"total": 1118.538328811,
"count": 1,
"self": 0.38729116299987254,
"children": {
"run_training.setup": {
"total": 0.10822928800007503,
"count": 1,
"self": 0.10822928800007503
},
"TrainerController.start_learning": {
"total": 1118.04280836,
"count": 1,
"self": 1.339404615007652,
"children": {
"TrainerController._reset_env": {
"total": 7.860768500999939,
"count": 1,
"self": 7.860768500999939
},
"TrainerController.advance": {
"total": 1108.725483562992,
"count": 45476,
"self": 0.6476338240406676,
"children": {
"env_step": {
"total": 1108.0778497389513,
"count": 45476,
"self": 756.0836853009353,
"children": {
"SubprocessEnvManager._take_step": {
"total": 351.3607742720128,
"count": 45476,
"self": 3.586536988024136,
"children": {
"TorchPolicy.evaluate": {
"total": 347.77423728398867,
"count": 45476,
"self": 77.80760398403754,
"children": {
"TorchPolicy.sample_actions": {
"total": 269.9666332999511,
"count": 45476,
"self": 269.9666332999511
}
}
}
}
},
"workers": {
"total": 0.6333901660032097,
"count": 45476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1114.3304624219884,
"count": 45476,
"is_parallel": true,
"self": 534.9895839689591,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002102020999927845,
"count": 1,
"is_parallel": true,
"self": 0.0007405280000511993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013614929998766456,
"count": 10,
"is_parallel": true,
"self": 0.0013614929998766456
}
}
},
"UnityEnvironment.step": {
"total": 0.07253725500004293,
"count": 1,
"is_parallel": true,
"self": 0.0005636210000830033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041451399988545745,
"count": 1,
"is_parallel": true,
"self": 0.00041451399988545745
},
"communicator.exchange": {
"total": 0.06970316499996443,
"count": 1,
"is_parallel": true,
"self": 0.06970316499996443
},
"steps_from_proto": {
"total": 0.0018559550001100433,
"count": 1,
"is_parallel": true,
"self": 0.0004475619998629554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001408393000247088,
"count": 10,
"is_parallel": true,
"self": 0.001408393000247088
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 579.3408784530293,
"count": 45475,
"is_parallel": true,
"self": 23.198360570102295,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.781568951963663,
"count": 45475,
"is_parallel": true,
"self": 12.781568951963663
},
"communicator.exchange": {
"total": 458.63768178096643,
"count": 45475,
"is_parallel": true,
"self": 458.63768178096643
},
"steps_from_proto": {
"total": 84.7232671499969,
"count": 45475,
"is_parallel": true,
"self": 17.40150528506706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.32176186492984,
"count": 454750,
"is_parallel": true,
"self": 67.32176186492984
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001947270002347068,
"count": 1,
"self": 0.0001947270002347068,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1100.30309579797,
"count": 1010548,
"is_parallel": true,
"self": 25.530554726966784,
"children": {
"process_trajectory": {
"total": 626.6469036679989,
"count": 1010548,
"is_parallel": true,
"self": 624.8285407359988,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8183629320001273,
"count": 10,
"is_parallel": true,
"self": 1.8183629320001273
}
}
},
"_update_policy": {
"total": 448.12563740300425,
"count": 227,
"is_parallel": true,
"self": 155.7001612769957,
"children": {
"TorchPPOOptimizer.update": {
"total": 292.42547612600856,
"count": 11574,
"is_parallel": true,
"self": 292.42547612600856
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11695695400021577,
"count": 1,
"self": 0.0009245850001207145,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11603236900009506,
"count": 1,
"self": 0.11603236900009506
}
}
}
}
}
}
}