Michal-Miszcz's picture
First Push
e46397e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.143898606300354,
"min": 1.143898606300354,
"max": 2.8686203956604004,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10934.5263671875,
"min": 10934.5263671875,
"max": 29377.541015625,
"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": 12.324942588806152,
"min": 0.37494906783103943,
"max": 12.324942588806152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2403.36376953125,
"min": 72.74011993408203,
"max": 2462.221923828125,
"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": 0.06779716312531474,
"min": 0.0631944042904412,
"max": 0.07394618451020078,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27118865250125895,
"min": 0.2564861155023762,
"max": 0.3697309225510039,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2098699978315363,
"min": 0.13291517545711068,
"max": 0.28750859288608327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8394799913261451,
"min": 0.5316607018284427,
"max": 1.2853238833885565,
"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": 24.75,
"min": 3.590909090909091,
"max": 24.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1089.0,
"min": 158.0,
"max": 1311.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.75,
"min": 3.590909090909091,
"max": 24.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1089.0,
"min": 158.0,
"max": 1311.0,
"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": "1702376774",
"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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702377262"
},
"total": 488.035257965,
"count": 1,
"self": 0.4241585860002033,
"children": {
"run_training.setup": {
"total": 0.05834114499998577,
"count": 1,
"self": 0.05834114499998577
},
"TrainerController.start_learning": {
"total": 487.55275823399984,
"count": 1,
"self": 0.6320534640215101,
"children": {
"TrainerController._reset_env": {
"total": 2.9508827360000396,
"count": 1,
"self": 2.9508827360000396
},
"TrainerController.advance": {
"total": 483.8839016129782,
"count": 18200,
"self": 0.2963725769836856,
"children": {
"env_step": {
"total": 483.5875290359945,
"count": 18200,
"self": 329.4978186679757,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.77638239400267,
"count": 18200,
"self": 1.555952486968863,
"children": {
"TorchPolicy.evaluate": {
"total": 152.2204299070338,
"count": 18200,
"self": 152.2204299070338
}
}
},
"workers": {
"total": 0.313327974016147,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.21533618599574,
"count": 18200,
"is_parallel": true,
"self": 236.13772866300747,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021745149999787827,
"count": 1,
"is_parallel": true,
"self": 0.0007168019997152442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014577130002635386,
"count": 10,
"is_parallel": true,
"self": 0.0014577130002635386
}
}
},
"UnityEnvironment.step": {
"total": 0.03511290400001599,
"count": 1,
"is_parallel": true,
"self": 0.0005959720001555979,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003989760000422393,
"count": 1,
"is_parallel": true,
"self": 0.0003989760000422393
},
"communicator.exchange": {
"total": 0.03220808999981273,
"count": 1,
"is_parallel": true,
"self": 0.03220808999981273
},
"steps_from_proto": {
"total": 0.0019098660000054224,
"count": 1,
"is_parallel": true,
"self": 0.00037477800015039975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015350879998550226,
"count": 10,
"is_parallel": true,
"self": 0.0015350879998550226
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.07760752298827,
"count": 18199,
"is_parallel": true,
"self": 10.752228057967613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.430432527015682,
"count": 18199,
"is_parallel": true,
"self": 5.430432527015682
},
"communicator.exchange": {
"total": 198.9159366339943,
"count": 18199,
"is_parallel": true,
"self": 198.9159366339943
},
"steps_from_proto": {
"total": 34.97901030401067,
"count": 18199,
"is_parallel": true,
"self": 6.902097870066655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.076912433944017,
"count": 181990,
"is_parallel": true,
"self": 28.076912433944017
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001297140001952357,
"count": 1,
"self": 0.0001297140001952357,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 479.86153458597323,
"count": 485616,
"is_parallel": true,
"self": 10.578466904987636,
"children": {
"process_trajectory": {
"total": 273.6468871479865,
"count": 485616,
"is_parallel": true,
"self": 266.98634063798636,
"children": {
"RLTrainer._checkpoint": {
"total": 6.660546510000131,
"count": 40,
"is_parallel": true,
"self": 6.660546510000131
}
}
},
"_update_policy": {
"total": 195.6361805329991,
"count": 90,
"is_parallel": true,
"self": 60.18595051899206,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.45023001400705,
"count": 4587,
"is_parallel": true,
"self": 135.45023001400705
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08579070699988733,
"count": 1,
"self": 0.001195408999819847,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08459529800006749,
"count": 1,
"self": 0.08459529800006749
}
}
}
}
}
}
}