Dawit-N's picture
First Push
ef1e1f6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8105825185775757,
"min": 0.7958863973617554,
"max": 2.863117218017578,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7703.7763671875,
"min": 7703.7763671875,
"max": 29226.701171875,
"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": 12.120932579040527,
"min": 0.32257387042045593,
"max": 12.120932579040527,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2363.581787109375,
"min": 62.57933044433594,
"max": 2463.7138671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06344500845924296,
"min": 0.06344500845924296,
"max": 0.07420229335020492,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25378003383697184,
"min": 0.25378003383697184,
"max": 0.36722503656632155,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17446895082499467,
"min": 0.12179475228813495,
"max": 0.2785173773765564,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6978758032999787,
"min": 0.4871790091525398,
"max": 1.392586886882782,
"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": 23.681818181818183,
"min": 3.4318181818181817,
"max": 24.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1042.0,
"min": 151.0,
"max": 1310.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.681818181818183,
"min": 3.4318181818181817,
"max": 24.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1042.0,
"min": 151.0,
"max": 1310.0,
"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": "1745233604",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1745234028"
},
"total": 423.62487665000003,
"count": 1,
"self": 0.4871033620001981,
"children": {
"run_training.setup": {
"total": 0.022455919999856633,
"count": 1,
"self": 0.022455919999856633
},
"TrainerController.start_learning": {
"total": 423.115317368,
"count": 1,
"self": 0.30878145098768073,
"children": {
"TrainerController._reset_env": {
"total": 3.1281202229999963,
"count": 1,
"self": 3.1281202229999963
},
"TrainerController.advance": {
"total": 419.5917057510121,
"count": 18192,
"self": 0.33702883899786684,
"children": {
"env_step": {
"total": 295.4198882010105,
"count": 18192,
"self": 224.59727054405812,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.61889911697358,
"count": 18192,
"self": 1.2354075909668154,
"children": {
"TorchPolicy.evaluate": {
"total": 69.38349152600676,
"count": 18192,
"self": 69.38349152600676
}
}
},
"workers": {
"total": 0.20371853997880862,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.7223906610134,
"count": 18192,
"is_parallel": true,
"self": 224.55351382201684,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005309677000013835,
"count": 1,
"is_parallel": true,
"self": 0.0038323090000176308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014773679999962042,
"count": 10,
"is_parallel": true,
"self": 0.0014773679999962042
}
}
},
"UnityEnvironment.step": {
"total": 0.03453195500014772,
"count": 1,
"is_parallel": true,
"self": 0.000576740000042264,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037313799998628383,
"count": 1,
"is_parallel": true,
"self": 0.00037313799998628383
},
"communicator.exchange": {
"total": 0.03173734899996816,
"count": 1,
"is_parallel": true,
"self": 0.03173734899996816
},
"steps_from_proto": {
"total": 0.001844728000151008,
"count": 1,
"is_parallel": true,
"self": 0.00037282400035110186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014719039997999062,
"count": 10,
"is_parallel": true,
"self": 0.0014719039997999062
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.16887683899654,
"count": 18191,
"is_parallel": true,
"self": 9.779723637008146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2562249000072825,
"count": 18191,
"is_parallel": true,
"self": 5.2562249000072825
},
"communicator.exchange": {
"total": 151.2409629039821,
"count": 18191,
"is_parallel": true,
"self": 151.2409629039821
},
"steps_from_proto": {
"total": 30.891965397999,
"count": 18191,
"is_parallel": true,
"self": 5.422091290954995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.469874107044006,
"count": 181910,
"is_parallel": true,
"self": 25.469874107044006
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.83478871100374,
"count": 18192,
"self": 0.3941574639939063,
"children": {
"process_trajectory": {
"total": 26.902397471008726,
"count": 18192,
"self": 26.412983264008744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4894142069999816,
"count": 4,
"self": 0.4894142069999816
}
}
},
"_update_policy": {
"total": 96.5382337760011,
"count": 90,
"self": 37.99540154099964,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.54283223500147,
"count": 4587,
"self": 58.54283223500147
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.34000127017498e-07,
"count": 1,
"self": 9.34000127017498e-07
},
"TrainerController._save_models": {
"total": 0.08670900900006018,
"count": 1,
"self": 0.0007385180001620029,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08597049099989817,
"count": 1,
"self": 0.08597049099989817
}
}
}
}
}
}
}