vinh406's picture
First Push
fb6c538 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1157130002975464,
"min": 1.1157130002975464,
"max": 2.8470702171325684,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10603.736328125,
"min": 10603.736328125,
"max": 29062.892578125,
"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": 12.168549537658691,
"min": 0.41863560676574707,
"max": 12.168549537658691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2372.8671875,
"min": 81.2153091430664,
"max": 2478.28466796875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0646198294517115,
"min": 0.06393948221047335,
"max": 0.07600054958043165,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.258479317806846,
"min": 0.2557579288418934,
"max": 0.3800027479021582,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2009039937573321,
"min": 0.17075353336529622,
"max": 0.27961056448665317,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8036159750293284,
"min": 0.6830141334611849,
"max": 1.3980528224332658,
"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.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.Environment.CumulativeReward.mean": {
"value": 23.704545454545453,
"min": 4.181818181818182,
"max": 24.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1043.0,
"min": 184.0,
"max": 1320.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.704545454545453,
"min": 4.181818181818182,
"max": 24.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1043.0,
"min": 184.0,
"max": 1320.0,
"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": "1771928021",
"python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]",
"command_line_arguments": "/home/vinhnt/projects/deep-rl-class/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1771928447"
},
"total": 425.2558759979984,
"count": 1,
"self": 0.2209358279942535,
"children": {
"run_training.setup": {
"total": 0.020029753002745565,
"count": 1,
"self": 0.020029753002745565
},
"TrainerController.start_learning": {
"total": 425.0149104170014,
"count": 1,
"self": 0.3560875709663378,
"children": {
"TrainerController._reset_env": {
"total": 2.967672830000083,
"count": 1,
"self": 2.967672830000083
},
"TrainerController.advance": {
"total": 421.6198162780347,
"count": 18192,
"self": 0.2907682898476196,
"children": {
"env_step": {
"total": 320.5339333891352,
"count": 18192,
"self": 240.63347137506207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.68144729793858,
"count": 18192,
"self": 1.0645867622224614,
"children": {
"TorchPolicy.evaluate": {
"total": 78.61686053571611,
"count": 18192,
"self": 78.61686053571611
}
}
},
"workers": {
"total": 0.21901471613455215,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.0403310439651,
"count": 18192,
"is_parallel": true,
"self": 203.6959198896766,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021774990018457174,
"count": 1,
"is_parallel": true,
"self": 0.0011674520101223607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010100469917233568,
"count": 10,
"is_parallel": true,
"self": 0.0010100469917233568
}
}
},
"UnityEnvironment.step": {
"total": 0.020333549000497442,
"count": 1,
"is_parallel": true,
"self": 0.0002492949970474001,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001565910024510231,
"count": 1,
"is_parallel": true,
"self": 0.0001565910024510231
},
"communicator.exchange": {
"total": 0.019308342001750134,
"count": 1,
"is_parallel": true,
"self": 0.019308342001750134
},
"steps_from_proto": {
"total": 0.0006193209992488846,
"count": 1,
"is_parallel": true,
"self": 0.00014266200014390051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004766589991049841,
"count": 10,
"is_parallel": true,
"self": 0.0004766589991049841
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.34441115428854,
"count": 18191,
"is_parallel": true,
"self": 3.538752132153604,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.163269102053164,
"count": 18191,
"is_parallel": true,
"self": 2.163269102053164
},
"communicator.exchange": {
"total": 204.63057950809525,
"count": 18191,
"is_parallel": true,
"self": 204.63057950809525
},
"steps_from_proto": {
"total": 10.011810411986517,
"count": 18191,
"is_parallel": true,
"self": 2.252565866278019,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.759244545708498,
"count": 181910,
"is_parallel": true,
"self": 7.759244545708498
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 100.79511459905189,
"count": 18192,
"self": 0.49114820293470984,
"children": {
"process_trajectory": {
"total": 22.953469249154296,
"count": 18192,
"self": 22.59225787115429,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36121137800000724,
"count": 4,
"self": 0.36121137800000724
}
}
},
"_update_policy": {
"total": 77.35049714696288,
"count": 90,
"self": 19.98501971594669,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.36547743101619,
"count": 4587,
"self": 57.36547743101619
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.9100057114847e-07,
"count": 1,
"self": 5.9100057114847e-07
},
"TrainerController._save_models": {
"total": 0.07133314699967741,
"count": 1,
"self": 0.0011911649999092333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07014198199976818,
"count": 1,
"self": 0.07014198199976818
}
}
}
}
}
}
}