ppo-Huggy / run_logs /timers.json
bocchi-julia's picture
Huggy
55f0c34 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030178785324097,
"min": 1.4030178785324097,
"max": 1.429017424583435,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68457.453125,
"min": 66597.84375,
"max": 79040.03125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.04421768707483,
"min": 80.15865384615384,
"max": 388.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49418.0,
"min": 48698.0,
"max": 50184.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49962.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49962.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3904201984405518,
"min": 0.06428151577711105,
"max": 2.4401443004608154,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1405.567138671875,
"min": 8.613722801208496,
"max": 1502.07470703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7127903875242283,
"min": 1.6029715763766375,
"max": 3.889397117349531,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2183.1207478642464,
"min": 214.7981912344694,
"max": 2322.705219209194,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7127903875242283,
"min": 1.6029715763766375,
"max": 3.889397117349531,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2183.1207478642464,
"min": 214.7981912344694,
"max": 2322.705219209194,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017364208586513996,
"min": 0.013817480747820807,
"max": 0.02181782053958159,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05209262575954199,
"min": 0.028704670290850724,
"max": 0.05722603258764139,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05436763171520498,
"min": 0.01999831375045081,
"max": 0.06367031422754128,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16310289514561493,
"min": 0.03999662750090162,
"max": 0.19061093342800933,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.287498904200007e-06,
"min": 3.287498904200007e-06,
"max": 0.00029530147656617496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.862496712600021e-06,
"min": 9.862496712600021e-06,
"max": 0.0008437896187367998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010958,
"min": 0.1010958,
"max": 0.198433825,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032874,
"min": 0.20735439999999997,
"max": 0.5812632,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.468042000000011e-05,
"min": 6.468042000000011e-05,
"max": 0.0049218478675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019404126000000034,
"min": 0.00019404126000000034,
"max": 0.014065033680000002,
"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": "1738337338",
"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": "1738339917"
},
"total": 2578.4736790529996,
"count": 1,
"self": 0.438536686999214,
"children": {
"run_training.setup": {
"total": 0.06080464799998708,
"count": 1,
"self": 0.06080464799998708
},
"TrainerController.start_learning": {
"total": 2577.9743377180002,
"count": 1,
"self": 4.753109455022695,
"children": {
"TrainerController._reset_env": {
"total": 5.27936349700002,
"count": 1,
"self": 5.27936349700002
},
"TrainerController.advance": {
"total": 2567.8147786659774,
"count": 231895,
"self": 4.891463358954297,
"children": {
"env_step": {
"total": 2035.7230677089967,
"count": 231895,
"self": 1595.394411220031,
"children": {
"SubprocessEnvManager._take_step": {
"total": 437.4028521328537,
"count": 231895,
"self": 16.352152142932653,
"children": {
"TorchPolicy.evaluate": {
"total": 421.05069998992104,
"count": 222820,
"self": 421.05069998992104
}
}
},
"workers": {
"total": 2.925804356111996,
"count": 231895,
"self": 0.0,
"children": {
"worker_root": {
"total": 2570.3960960870427,
"count": 231895,
"is_parallel": true,
"self": 1273.4946216040103,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009670440000490999,
"count": 1,
"is_parallel": true,
"self": 0.000282530000049519,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006845139999995808,
"count": 2,
"is_parallel": true,
"self": 0.0006845139999995808
}
}
},
"UnityEnvironment.step": {
"total": 0.031618861999959336,
"count": 1,
"is_parallel": true,
"self": 0.00040208699999766395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002063969999994697,
"count": 1,
"is_parallel": true,
"self": 0.0002063969999994697
},
"communicator.exchange": {
"total": 0.030147341999963828,
"count": 1,
"is_parallel": true,
"self": 0.030147341999963828
},
"steps_from_proto": {
"total": 0.0008630359999983739,
"count": 1,
"is_parallel": true,
"self": 0.00027480400007107164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005882319999273022,
"count": 2,
"is_parallel": true,
"self": 0.0005882319999273022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1296.9014744830324,
"count": 231894,
"is_parallel": true,
"self": 38.89682415585003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.64896945207624,
"count": 231894,
"is_parallel": true,
"self": 87.64896945207624
},
"communicator.exchange": {
"total": 1076.4786851390547,
"count": 231894,
"is_parallel": true,
"self": 1076.4786851390547
},
"steps_from_proto": {
"total": 93.87699573605136,
"count": 231894,
"is_parallel": true,
"self": 35.70696248996791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.17003324608345,
"count": 463788,
"is_parallel": true,
"self": 58.17003324608345
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.2002475980264,
"count": 231895,
"self": 6.75849234798693,
"children": {
"process_trajectory": {
"total": 174.48907838203826,
"count": 231895,
"self": 173.04697372303843,
"children": {
"RLTrainer._checkpoint": {
"total": 1.442104658999824,
"count": 10,
"self": 1.442104658999824
}
}
},
"_update_policy": {
"total": 345.95267686800116,
"count": 97,
"self": 278.54771448099086,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.4049623870103,
"count": 2910,
"self": 67.4049623870103
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5660002645745408e-06,
"count": 1,
"self": 1.5660002645745408e-06
},
"TrainerController._save_models": {
"total": 0.12708453400000508,
"count": 1,
"self": 0.002015179999943939,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12506935400006114,
"count": 1,
"self": 0.12506935400006114
}
}
}
}
}
}
}