ppo-Huggy-v1 / run_logs /timers.json
Adi-AI-2005's picture
Huggy is ready
7a29233 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404448390007019,
"min": 1.404448390007019,
"max": 1.429411768913269,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68788.4765625,
"min": 68788.4765625,
"max": 77158.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.16293279022403,
"min": 94.24858757062147,
"max": 405.81451612903226,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49180.0,
"min": 48815.0,
"max": 50321.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999664.0,
"min": 49695.0,
"max": 1999664.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999664.0,
"min": 49695.0,
"max": 1999664.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.384913206100464,
"min": 0.02542627975344658,
"max": 2.384913206100464,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1170.992431640625,
"min": 3.127432346343994,
"max": 1209.4251708984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7819201559010445,
"min": 1.8689328709511253,
"max": 3.8592431978745894,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1856.9227965474129,
"min": 229.8787431269884,
"max": 1910.3253829479218,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7819201559010445,
"min": 1.8689328709511253,
"max": 3.8592431978745894,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1856.9227965474129,
"min": 229.8787431269884,
"max": 1910.3253829479218,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015819711435809344,
"min": 0.013112420918575177,
"max": 0.019928182534931692,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03163942287161869,
"min": 0.026224841837150355,
"max": 0.054060009900664834,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05016690865159035,
"min": 0.024681978641698757,
"max": 0.06059608751287063,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1003338173031807,
"min": 0.049363957283397514,
"max": 0.17879654665788014,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.653248448949994e-06,
"min": 4.653248448949994e-06,
"max": 0.00029538907653697496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.306496897899988e-06,
"min": 9.306496897899988e-06,
"max": 0.0008441532186155998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155105000000002,
"min": 0.10155105000000002,
"max": 0.19846302500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310210000000004,
"min": 0.20310210000000004,
"max": 0.5813844,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.73973949999999e-05,
"min": 8.73973949999999e-05,
"max": 0.004923304947499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001747947899999998,
"min": 0.0001747947899999998,
"max": 0.01407108156,
"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": "1734787357",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734789929"
},
"total": 2571.9722352119998,
"count": 1,
"self": 0.43581280399939715,
"children": {
"run_training.setup": {
"total": 0.08283653600005891,
"count": 1,
"self": 0.08283653600005891
},
"TrainerController.start_learning": {
"total": 2571.453585872,
"count": 1,
"self": 4.831041411011938,
"children": {
"TrainerController._reset_env": {
"total": 5.3434079160000465,
"count": 1,
"self": 5.3434079160000465
},
"TrainerController.advance": {
"total": 2561.152535072988,
"count": 231166,
"self": 4.908334323756662,
"children": {
"env_step": {
"total": 2016.9026027480718,
"count": 231166,
"self": 1584.7791729860587,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.07210728891175,
"count": 231166,
"self": 16.086198315914203,
"children": {
"TorchPolicy.evaluate": {
"total": 412.98590897299755,
"count": 222880,
"self": 412.98590897299755
}
}
},
"workers": {
"total": 3.051322473101436,
"count": 231166,
"self": 0.0,
"children": {
"worker_root": {
"total": 2563.6171317600447,
"count": 231166,
"is_parallel": true,
"self": 1276.9067190810565,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011208230000647745,
"count": 1,
"is_parallel": true,
"self": 0.000340051000080166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007807719999846086,
"count": 2,
"is_parallel": true,
"self": 0.0007807719999846086
}
}
},
"UnityEnvironment.step": {
"total": 0.028913157000033607,
"count": 1,
"is_parallel": true,
"self": 0.0004094619999932547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020896900002753682,
"count": 1,
"is_parallel": true,
"self": 0.00020896900002753682
},
"communicator.exchange": {
"total": 0.027557257000012214,
"count": 1,
"is_parallel": true,
"self": 0.027557257000012214
},
"steps_from_proto": {
"total": 0.0007374690000006012,
"count": 1,
"is_parallel": true,
"self": 0.00019091799993020686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005465510000703944,
"count": 2,
"is_parallel": true,
"self": 0.0005465510000703944
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.7104126789882,
"count": 231165,
"is_parallel": true,
"self": 39.25663239714913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.22594481694205,
"count": 231165,
"is_parallel": true,
"self": 85.22594481694205
},
"communicator.exchange": {
"total": 1069.0192124969653,
"count": 231165,
"is_parallel": true,
"self": 1069.0192124969653
},
"steps_from_proto": {
"total": 93.20862296793166,
"count": 231165,
"is_parallel": true,
"self": 34.8867856439914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.32183732394026,
"count": 462330,
"is_parallel": true,
"self": 58.32183732394026
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 539.3415980011596,
"count": 231166,
"self": 7.182713723146776,
"children": {
"process_trajectory": {
"total": 166.16116311601456,
"count": 231166,
"self": 164.88095938001413,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2802037360004306,
"count": 10,
"self": 1.2802037360004306
}
}
},
"_update_policy": {
"total": 365.99772116199824,
"count": 96,
"self": 295.9109659780024,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.08675518399582,
"count": 2880,
"self": 70.08675518399582
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.032999989547534e-06,
"count": 1,
"self": 1.032999989547534e-06
},
"TrainerController._save_models": {
"total": 0.126600438999958,
"count": 1,
"self": 0.002060061000065616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12454037799989237,
"count": 1,
"self": 0.12454037799989237
}
}
}
}
}
}
}