ppo-Huggy / run_logs /timers.json
Iamvincent's picture
Huggy bonus
a7f6a72
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404797911643982,
"min": 1.404797911643982,
"max": 1.4254287481307983,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70980.2265625,
"min": 68912.2890625,
"max": 78464.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.77495107632095,
"min": 87.53886925795052,
"max": 427.7606837606838,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49452.0,
"min": 49058.0,
"max": 50151.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49557.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49557.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3750686645507812,
"min": -0.04765604808926582,
"max": 2.426619291305542,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1213.6600341796875,
"min": -5.528101444244385,
"max": 1367.8529052734375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6869954202039836,
"min": 1.8591121797417771,
"max": 4.014114565962837,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1884.0546597242355,
"min": 215.65701285004616,
"max": 2208.712694168091,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6869954202039836,
"min": 1.8591121797417771,
"max": 4.014114565962837,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1884.0546597242355,
"min": 215.65701285004616,
"max": 2208.712694168091,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013808970355158738,
"min": 0.012475302761837764,
"max": 0.019824845646508035,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04142691106547621,
"min": 0.024950605523675527,
"max": 0.055949381759273824,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051081322837207045,
"min": 0.022823897718141476,
"max": 0.055094809643924235,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15324396851162114,
"min": 0.04564779543628295,
"max": 0.16432322127123675,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3751988749666643e-06,
"min": 3.3751988749666643e-06,
"max": 0.00029531062656312497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0125596624899993e-05,
"min": 1.0125596624899993e-05,
"max": 0.0008440989186336999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112503333333335,
"min": 0.10112503333333335,
"max": 0.198436875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30337510000000006,
"min": 0.20739435,
"max": 0.5813662999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.61391633333333e-05,
"min": 6.61391633333333e-05,
"max": 0.0049220000625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001984174899999999,
"min": 0.0001984174899999999,
"max": 0.01407017837,
"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": "1671105291",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
"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": "1671107488"
},
"total": 2196.943454884,
"count": 1,
"self": 0.3885460179999427,
"children": {
"run_training.setup": {
"total": 0.10303083899998455,
"count": 1,
"self": 0.10303083899998455
},
"TrainerController.start_learning": {
"total": 2196.451878027,
"count": 1,
"self": 3.7501168999660877,
"children": {
"TrainerController._reset_env": {
"total": 6.140002964999894,
"count": 1,
"self": 6.140002964999894
},
"TrainerController.advance": {
"total": 2186.439649825034,
"count": 231976,
"self": 3.987265035124892,
"children": {
"env_step": {
"total": 1713.4818255938915,
"count": 231976,
"self": 1438.0433371126726,
"children": {
"SubprocessEnvManager._take_step": {
"total": 272.90519563104385,
"count": 231976,
"self": 14.201231323023194,
"children": {
"TorchPolicy.evaluate": {
"total": 258.70396430802066,
"count": 222988,
"self": 64.01051091291811,
"children": {
"TorchPolicy.sample_actions": {
"total": 194.69345339510255,
"count": 222988,
"self": 194.69345339510255
}
}
}
}
},
"workers": {
"total": 2.5332928501750303,
"count": 231976,
"self": 0.0,
"children": {
"worker_root": {
"total": 2188.8464156859523,
"count": 231976,
"is_parallel": true,
"self": 1002.3474017950148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007960410000578122,
"count": 1,
"is_parallel": true,
"self": 0.00028229200006535393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005137489999924583,
"count": 2,
"is_parallel": true,
"self": 0.0005137489999924583
}
}
},
"UnityEnvironment.step": {
"total": 0.027355456999885064,
"count": 1,
"is_parallel": true,
"self": 0.00026900199964075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020362500004011963,
"count": 1,
"is_parallel": true,
"self": 0.00020362500004011963
},
"communicator.exchange": {
"total": 0.025969770000074277,
"count": 1,
"is_parallel": true,
"self": 0.025969770000074277
},
"steps_from_proto": {
"total": 0.0009130600001299172,
"count": 1,
"is_parallel": true,
"self": 0.00042081700007656764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004922430000533495,
"count": 2,
"is_parallel": true,
"self": 0.0004922430000533495
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1186.4990138909375,
"count": 231975,
"is_parallel": true,
"self": 34.43793738298905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.06447597213423,
"count": 231975,
"is_parallel": true,
"self": 74.06447597213423
},
"communicator.exchange": {
"total": 986.7822099599048,
"count": 231975,
"is_parallel": true,
"self": 986.7822099599048
},
"steps_from_proto": {
"total": 91.21439057590942,
"count": 231975,
"is_parallel": true,
"self": 37.47646354087351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.73792703503591,
"count": 463950,
"is_parallel": true,
"self": 53.73792703503591
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 468.9705591960176,
"count": 231976,
"self": 6.000540766106951,
"children": {
"process_trajectory": {
"total": 144.74900452491124,
"count": 231976,
"self": 143.58371105891047,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1652934660007759,
"count": 10,
"self": 1.1652934660007759
}
}
},
"_update_policy": {
"total": 318.2210139049994,
"count": 97,
"self": 264.4457581909753,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.77525571402407,
"count": 2910,
"self": 53.77525571402407
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.400002116104588e-07,
"count": 1,
"self": 8.400002116104588e-07
},
"TrainerController._save_models": {
"total": 0.1221074969998881,
"count": 1,
"self": 0.004344192999724328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11776330400016377,
"count": 1,
"self": 0.11776330400016377
}
}
}
}
}
}
}