sid's picture
First Push
fc71f97
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8231903910636902,
"min": 0.8231903910636902,
"max": 2.8631677627563477,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7886.9873046875,
"min": 7886.9873046875,
"max": 29416.185546875,
"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": 13.05867862701416,
"min": 0.4177599251270294,
"max": 13.05867862701416,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2546.4423828125,
"min": 81.04542541503906,
"max": 2639.91748046875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06697875021285761,
"min": 0.06344544628373114,
"max": 0.08084832970309756,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26791500085143044,
"min": 0.2625175999253806,
"max": 0.37182227206786217,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2160446056548287,
"min": 0.10837748325909213,
"max": 0.2898864581888797,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8641784226193148,
"min": 0.43350993303636853,
"max": 1.4494322909443986,
"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": 25.545454545454547,
"min": 3.227272727272727,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 142.0,
"max": 1431.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.227272727272727,
"max": 26.01818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 142.0,
"max": 1431.0,
"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": "1688235432",
"python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]",
"command_line_arguments": "/home/sid/anaconda3/envs/ml_env_39/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688235665"
},
"total": 232.97133139200002,
"count": 1,
"self": 0.21765013400010957,
"children": {
"run_training.setup": {
"total": 0.009954407000009269,
"count": 1,
"self": 0.009954407000009269
},
"TrainerController.start_learning": {
"total": 232.7437268509999,
"count": 1,
"self": 0.32519725999384264,
"children": {
"TrainerController._reset_env": {
"total": 2.5428670339999826,
"count": 1,
"self": 2.5428670339999826
},
"TrainerController.advance": {
"total": 229.79843322800616,
"count": 18205,
"self": 0.15609324801528146,
"children": {
"env_step": {
"total": 229.64233997999088,
"count": 18205,
"self": 171.4889312059919,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.97911686799557,
"count": 18205,
"self": 0.7951457649929807,
"children": {
"TorchPolicy.evaluate": {
"total": 57.18397110300259,
"count": 18205,
"self": 57.18397110300259
}
}
},
"workers": {
"total": 0.17429190600341826,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 232.3474588089997,
"count": 18205,
"is_parallel": true,
"self": 112.48648273400113,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010971509999535556,
"count": 1,
"is_parallel": true,
"self": 0.0002913340001668985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008058169997866571,
"count": 10,
"is_parallel": true,
"self": 0.0008058169997866571
}
}
},
"UnityEnvironment.step": {
"total": 0.0161581259999366,
"count": 1,
"is_parallel": true,
"self": 0.000564742999927148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015323000002354092,
"count": 1,
"is_parallel": true,
"self": 0.00015323000002354092
},
"communicator.exchange": {
"total": 0.014755273999981,
"count": 1,
"is_parallel": true,
"self": 0.014755273999981
},
"steps_from_proto": {
"total": 0.0006848790000049121,
"count": 1,
"is_parallel": true,
"self": 0.00015680299986797763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005280760001369345,
"count": 10,
"is_parallel": true,
"self": 0.0005280760001369345
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 119.86097607499858,
"count": 18204,
"is_parallel": true,
"self": 6.405188836985872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.4979101510059536,
"count": 18204,
"is_parallel": true,
"self": 2.4979101510059536
},
"communicator.exchange": {
"total": 93.3474092819996,
"count": 18204,
"is_parallel": true,
"self": 93.3474092819996
},
"steps_from_proto": {
"total": 17.610467805007147,
"count": 18204,
"is_parallel": true,
"self": 3.0617693429832116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.548698462023935,
"count": 182040,
"is_parallel": true,
"self": 14.548698462023935
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.080099990413146e-05,
"count": 1,
"self": 6.080099990413146e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 229.61291391096677,
"count": 134939,
"is_parallel": true,
"self": 1.2222192369639515,
"children": {
"process_trajectory": {
"total": 130.12167997200288,
"count": 134939,
"is_parallel": true,
"self": 129.64936393400285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47231603800003086,
"count": 4,
"is_parallel": true,
"self": 0.47231603800003086
}
}
},
"_update_policy": {
"total": 98.26901470199994,
"count": 90,
"is_parallel": true,
"self": 25.063870021997218,
"children": {
"TorchPPOOptimizer.update": {
"total": 73.20514468000272,
"count": 4587,
"is_parallel": true,
"self": 73.20514468000272
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07716852800001561,
"count": 1,
"self": 0.0004654370000025665,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07670309100001305,
"count": 1,
"self": 0.07670309100001305
}
}
}
}
}
}
}