HaythamB's picture
First Push
80437f4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7181148529052734,
"min": 0.7181148529052734,
"max": 2.865483522415161,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6864.4599609375,
"min": 6864.4599609375,
"max": 29439.9765625,
"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": 11.953082084655762,
"min": 0.27552908658981323,
"max": 11.953082084655762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2330.85107421875,
"min": 53.45264434814453,
"max": 2400.51123046875,
"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": 0.06336202845526642,
"min": 0.06153699209458222,
"max": 0.07361254313065158,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2534481138210657,
"min": 0.2493683053625693,
"max": 0.35326535945904314,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20461714735218123,
"min": 0.11507926228246194,
"max": 0.2800862081348896,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8184685894087249,
"min": 0.4603170491298478,
"max": 1.3391499282682644,
"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": 23.454545454545453,
"min": 3.159090909090909,
"max": 23.654545454545456,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1032.0,
"min": 139.0,
"max": 1301.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.454545454545453,
"min": 3.159090909090909,
"max": 23.654545454545456,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1032.0,
"min": 139.0,
"max": 1301.0,
"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": "1704036734",
"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": "1704037183"
},
"total": 448.55903829399995,
"count": 1,
"self": 0.44235958799981745,
"children": {
"run_training.setup": {
"total": 0.09184025100000781,
"count": 1,
"self": 0.09184025100000781
},
"TrainerController.start_learning": {
"total": 448.0248384550001,
"count": 1,
"self": 0.5577810540132759,
"children": {
"TrainerController._reset_env": {
"total": 3.157485276000102,
"count": 1,
"self": 3.157485276000102
},
"TrainerController.advance": {
"total": 444.2202633909867,
"count": 18200,
"self": 0.2658299310005532,
"children": {
"env_step": {
"total": 443.95443345998615,
"count": 18200,
"self": 292.6011119410109,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.06310670198593,
"count": 18200,
"self": 1.4461005249791015,
"children": {
"TorchPolicy.evaluate": {
"total": 149.61700617700683,
"count": 18200,
"self": 149.61700617700683
}
}
},
"workers": {
"total": 0.2902148169893053,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.90758094999535,
"count": 18200,
"is_parallel": true,
"self": 220.00733105701795,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004494512000064788,
"count": 1,
"is_parallel": true,
"self": 0.0031072209998228573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013872910002419303,
"count": 10,
"is_parallel": true,
"self": 0.0013872910002419303
}
}
},
"UnityEnvironment.step": {
"total": 0.037969208999925286,
"count": 1,
"is_parallel": true,
"self": 0.0006991210000251158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003793099999711558,
"count": 1,
"is_parallel": true,
"self": 0.0003793099999711558
},
"communicator.exchange": {
"total": 0.03449052700000266,
"count": 1,
"is_parallel": true,
"self": 0.03449052700000266
},
"steps_from_proto": {
"total": 0.0024002509999263566,
"count": 1,
"is_parallel": true,
"self": 0.0006055239996385353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017947270002878213,
"count": 10,
"is_parallel": true,
"self": 0.0017947270002878213
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.9002498929774,
"count": 18199,
"is_parallel": true,
"self": 10.78329271399707,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.245401015991092,
"count": 18199,
"is_parallel": true,
"self": 5.245401015991092
},
"communicator.exchange": {
"total": 176.88114896799493,
"count": 18199,
"is_parallel": true,
"self": 176.88114896799493
},
"steps_from_proto": {
"total": 33.990407194994305,
"count": 18199,
"is_parallel": true,
"self": 6.2521371710209905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.738270023973314,
"count": 181990,
"is_parallel": true,
"self": 27.738270023973314
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013020400001551025,
"count": 1,
"self": 0.00013020400001551025,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.50607487707623,
"count": 688285,
"is_parallel": true,
"self": 14.20634569401841,
"children": {
"process_trajectory": {
"total": 241.4167477330575,
"count": 688285,
"is_parallel": true,
"self": 240.6585089900575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7582387429999926,
"count": 4,
"is_parallel": true,
"self": 0.7582387429999926
}
}
},
"_update_policy": {
"total": 182.88298145000033,
"count": 90,
"is_parallel": true,
"self": 59.83070938400351,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.05227206599682,
"count": 4587,
"is_parallel": true,
"self": 123.05227206599682
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08917853000002651,
"count": 1,
"self": 0.0010212830000000395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08815724700002647,
"count": 1,
"self": 0.08815724700002647
}
}
}
}
}
}
}