kingabzpro's picture
First PushBlock
dcd2bfa
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"PushBlock.Policy.Entropy.mean": {
"value": 1.8362246751785278,
"min": 1.8362246751785278,
"max": 1.8362246751785278,
"count": 1
},
"PushBlock.Policy.Entropy.sum": {
"value": 111407.421875,
"min": 111407.421875,
"max": 111407.421875,
"count": 1
},
"PushBlock.Step.mean": {
"value": 59966.0,
"min": 59966.0,
"max": 59966.0,
"count": 1
},
"PushBlock.Step.sum": {
"value": 59966.0,
"min": 59966.0,
"max": 59966.0,
"count": 1
},
"PushBlock.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.039823707193136215,
"min": 0.039823707193136215,
"max": 0.039823707193136215,
"count": 1
},
"PushBlock.Policy.ExtrinsicValueEstimate.sum": {
"value": 37.91217041015625,
"min": 37.91217041015625,
"max": 37.91217041015625,
"count": 1
},
"PushBlock.Losses.PolicyLoss.mean": {
"value": 0.06704430964122698,
"min": 0.06704430964122698,
"max": 0.06704430964122698,
"count": 1
},
"PushBlock.Losses.PolicyLoss.sum": {
"value": 1.2738418831833127,
"min": 1.2738418831833127,
"max": 1.2738418831833127,
"count": 1
},
"PushBlock.Losses.ValueLoss.mean": {
"value": 0.03694163520098852,
"min": 0.03694163520098852,
"max": 0.03694163520098852,
"count": 1
},
"PushBlock.Losses.ValueLoss.sum": {
"value": 0.7018910688187818,
"min": 0.7018910688187818,
"max": 0.7018910688187818,
"count": 1
},
"PushBlock.Policy.LearningRate.mean": {
"value": 0.00029475132017061316,
"min": 0.00029475132017061316,
"max": 0.00029475132017061316,
"count": 1
},
"PushBlock.Policy.LearningRate.sum": {
"value": 0.00560027508324165,
"min": 0.00560027508324165,
"max": 0.00560027508324165,
"count": 1
},
"PushBlock.Policy.Epsilon.mean": {
"value": 0.1982504394736842,
"min": 0.1982504394736842,
"max": 0.1982504394736842,
"count": 1
},
"PushBlock.Policy.Epsilon.sum": {
"value": 3.76675835,
"min": 3.76675835,
"max": 3.76675835,
"count": 1
},
"PushBlock.Policy.Beta.mean": {
"value": 0.009825218903421052,
"min": 0.009825218903421052,
"max": 0.009825218903421052,
"count": 1
},
"PushBlock.Policy.Beta.sum": {
"value": 0.18667915916499997,
"min": 0.18667915916499997,
"max": 0.18667915916499997,
"count": 1
},
"PushBlock.Environment.EpisodeLength.mean": {
"value": 854.95,
"min": 854.95,
"max": 854.95,
"count": 1
},
"PushBlock.Environment.EpisodeLength.sum": {
"value": 34198.0,
"min": 34198.0,
"max": 34198.0,
"count": 1
},
"PushBlock.Environment.CumulativeReward.mean": {
"value": 0.144124960526824,
"min": 0.144124960526824,
"max": 0.144124960526824,
"count": 1
},
"PushBlock.Environment.CumulativeReward.sum": {
"value": 5.76499842107296,
"min": 5.76499842107296,
"max": 5.76499842107296,
"count": 1
},
"PushBlock.Policy.ExtrinsicReward.mean": {
"value": 0.144124960526824,
"min": 0.144124960526824,
"max": 0.144124960526824,
"count": 1
},
"PushBlock.Policy.ExtrinsicReward.sum": {
"value": 5.76499842107296,
"min": 5.76499842107296,
"max": 5.76499842107296,
"count": 1
},
"PushBlock.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"PushBlock.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1656924741",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1656924815"
},
"total": 74.59077404699997,
"count": 1,
"self": 0.3834815720000506,
"children": {
"run_training.setup": {
"total": 0.042870317999927465,
"count": 1,
"self": 0.042870317999927465
},
"TrainerController.start_learning": {
"total": 74.16442215699999,
"count": 1,
"self": 0.048753984000541095,
"children": {
"TrainerController._reset_env": {
"total": 8.632162429000005,
"count": 1,
"self": 8.632162429000005
},
"TrainerController.advance": {
"total": 65.48297698799945,
"count": 2245,
"self": 0.05526459400175554,
"children": {
"env_step": {
"total": 37.81425027399973,
"count": 2245,
"self": 34.09187190299599,
"children": {
"SubprocessEnvManager._take_step": {
"total": 3.6983563540014757,
"count": 2245,
"self": 0.18426225000007435,
"children": {
"TorchPolicy.evaluate": {
"total": 3.5140941040014013,
"count": 2237,
"self": 1.091724532001649,
"children": {
"TorchPolicy.sample_actions": {
"total": 2.4223695719997522,
"count": 2237,
"self": 2.4223695719997522
}
}
}
}
},
"workers": {
"total": 0.024022017002266693,
"count": 2244,
"self": 0.0,
"children": {
"worker_root": {
"total": 74.08486261399912,
"count": 2244,
"is_parallel": true,
"self": 44.6305240420005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005512229000032676,
"count": 1,
"is_parallel": true,
"self": 0.00381649600012679,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016957329999058857,
"count": 4,
"is_parallel": true,
"self": 0.0016957329999058857
}
}
},
"UnityEnvironment.step": {
"total": 0.035090766999928746,
"count": 1,
"is_parallel": true,
"self": 0.0007449989998349338,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007464210000307503,
"count": 1,
"is_parallel": true,
"self": 0.0007464210000307503
},
"communicator.exchange": {
"total": 0.0313733369999909,
"count": 1,
"is_parallel": true,
"self": 0.0313733369999909
},
"steps_from_proto": {
"total": 0.002226010000072165,
"count": 1,
"is_parallel": true,
"self": 0.00043967600004179985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017863340000303651,
"count": 4,
"is_parallel": true,
"self": 0.0017863340000303651
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 29.45433857199862,
"count": 2243,
"is_parallel": true,
"self": 1.4206518659983658,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.466212650000216,
"count": 2243,
"is_parallel": true,
"self": 1.466212650000216
},
"communicator.exchange": {
"total": 22.032857154000453,
"count": 2243,
"is_parallel": true,
"self": 22.032857154000453
},
"steps_from_proto": {
"total": 4.534616901999584,
"count": 2243,
"is_parallel": true,
"self": 0.8396178719958698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.6949990300037143,
"count": 8972,
"is_parallel": true,
"self": 3.6949990300037143
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 27.613462119997962,
"count": 2244,
"self": 0.06752446899633924,
"children": {
"process_trajectory": {
"total": 6.781744252001886,
"count": 2244,
"self": 6.781744252001886
},
"_update_policy": {
"total": 20.764193398999737,
"count": 24,
"self": 11.137951236002436,
"children": {
"TorchPPOOptimizer.update": {
"total": 9.6262421629973,
"count": 1623,
"self": 9.6262421629973
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7050000451490632e-06,
"count": 1,
"self": 1.7050000451490632e-06
},
"TrainerController._save_models": {
"total": 0.0005270509999490969,
"count": 1,
"self": 2.5002999905154866e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.000502048000043942,
"count": 1,
"self": 0.000502048000043942
}
}
}
}
}
}
}