PPO-Huggy / run_logs /timers.json
Taranosaurus's picture
Huggy
0b9aea3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4112908840179443,
"min": 1.4112908840179443,
"max": 1.4306526184082031,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70434.703125,
"min": 69343.53125,
"max": 76538.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.84710017574693,
"min": 82.93781512605042,
"max": 396.40157480314963,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49416.0,
"min": 48847.0,
"max": 50343.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999932.0,
"min": 49720.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999932.0,
"min": 49720.0,
"max": 1999932.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3725383281707764,
"min": -0.05879661440849304,
"max": 2.4317145347595215,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1349.974365234375,
"min": -7.4083733558654785,
"max": 1407.301025390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6999285523836978,
"min": 1.8542908156320217,
"max": 3.904824068789841,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2105.259346306324,
"min": 233.64064276963472,
"max": 2206.394300699234,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6999285523836978,
"min": 1.8542908156320217,
"max": 3.904824068789841,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2105.259346306324,
"min": 233.64064276963472,
"max": 2206.394300699234,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01843379914579499,
"min": 0.013621437800854133,
"max": 0.021065496879358155,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05530139743738498,
"min": 0.027242875601708266,
"max": 0.05774364848815215,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05109763501418962,
"min": 0.022478514133642116,
"max": 0.06119583323597908,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15329290504256884,
"min": 0.04495702826728423,
"max": 0.18358749970793725,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.147448950883338e-06,
"min": 3.147448950883338e-06,
"max": 0.0002953197015601,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.442346852650014e-06,
"min": 9.442346852650014e-06,
"max": 0.0008438344687218499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104911666666667,
"min": 0.10104911666666667,
"max": 0.19843990000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30314735000000004,
"min": 0.20723324999999998,
"max": 0.58127815,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.235092166666672e-05,
"min": 6.235092166666672e-05,
"max": 0.0049221510100000004,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018705276500000017,
"min": 0.00018705276500000017,
"max": 0.014065779685,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1729822118",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729824478"
},
"total": 2360.489122006,
"count": 1,
"self": 0.4247026759999244,
"children": {
"run_training.setup": {
"total": 0.054146680000030756,
"count": 1,
"self": 0.054146680000030756
},
"TrainerController.start_learning": {
"total": 2360.01027265,
"count": 1,
"self": 4.237617972948101,
"children": {
"TrainerController._reset_env": {
"total": 5.2754420889999665,
"count": 1,
"self": 5.2754420889999665
},
"TrainerController.advance": {
"total": 2350.3830536980518,
"count": 231955,
"self": 4.18433222107069,
"children": {
"env_step": {
"total": 1849.6823830330056,
"count": 231955,
"self": 1450.7424654998947,
"children": {
"SubprocessEnvManager._take_step": {
"total": 396.3169575220636,
"count": 231955,
"self": 15.654309512089185,
"children": {
"TorchPolicy.evaluate": {
"total": 380.6626480099744,
"count": 222859,
"self": 380.6626480099744
}
}
},
"workers": {
"total": 2.6229600110473257,
"count": 231955,
"self": 0.0,
"children": {
"worker_root": {
"total": 2353.1886433830355,
"count": 231955,
"is_parallel": true,
"self": 1178.2290731219816,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000846969999997782,
"count": 1,
"is_parallel": true,
"self": 0.00021421100007046334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006327589999273187,
"count": 2,
"is_parallel": true,
"self": 0.0006327589999273187
}
}
},
"UnityEnvironment.step": {
"total": 0.050070983999944474,
"count": 1,
"is_parallel": true,
"self": 0.0003634819997841987,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001666490001070997,
"count": 1,
"is_parallel": true,
"self": 0.0001666490001070997
},
"communicator.exchange": {
"total": 0.04881548700006988,
"count": 1,
"is_parallel": true,
"self": 0.04881548700006988
},
"steps_from_proto": {
"total": 0.0007253659999832962,
"count": 1,
"is_parallel": true,
"self": 0.00021747399989635596,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005078920000869402,
"count": 2,
"is_parallel": true,
"self": 0.0005078920000869402
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1174.9595702610538,
"count": 231954,
"is_parallel": true,
"self": 36.56970704991977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.02759058307049,
"count": 231954,
"is_parallel": true,
"self": 78.02759058307049
},
"communicator.exchange": {
"total": 974.8597438340123,
"count": 231954,
"is_parallel": true,
"self": 974.8597438340123
},
"steps_from_proto": {
"total": 85.50252879405127,
"count": 231954,
"is_parallel": true,
"self": 30.680820405163217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.821708388888055,
"count": 463908,
"is_parallel": true,
"self": 54.821708388888055
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 496.5163384439753,
"count": 231955,
"self": 6.225945901985597,
"children": {
"process_trajectory": {
"total": 159.0270097179898,
"count": 231955,
"self": 157.6789508679899,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3480588499999158,
"count": 10,
"self": 1.3480588499999158
}
}
},
"_update_policy": {
"total": 331.2633828239999,
"count": 97,
"self": 265.5838656879954,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.6795171360045,
"count": 2910,
"self": 65.6795171360045
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.69999746303074e-07,
"count": 1,
"self": 9.69999746303074e-07
},
"TrainerController._save_models": {
"total": 0.11415792000025249,
"count": 1,
"self": 0.002075167000384681,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11208275299986781,
"count": 1,
"self": 0.11208275299986781
}
}
}
}
}
}
}