meiyun1995's picture
First Push
14b41ef verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7827969193458557,
"min": 0.7827969193458557,
"max": 1.5628265142440796,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 23220.888671875,
"min": 23220.888671875,
"max": 47409.90625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989894.0,
"min": 29952.0,
"max": 989894.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3479819595813751,
"min": -0.11442319303750992,
"max": 0.3479819595813751,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 90.47531127929688,
"min": -27.57598876953125,
"max": 90.47531127929688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.07742214947938919,
"min": -0.18604448437690735,
"max": 0.10150593519210815,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 20.129758834838867,
"min": -48.37156677246094,
"max": 25.376483917236328,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06948793411304775,
"min": 0.06383320813182043,
"max": 0.07493888481520744,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9728310775826685,
"min": 0.49440039051549467,
"max": 1.066275676536883,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01949131757144295,
"min": 3.903911380309218e-05,
"max": 0.01949131757144295,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2728784460002013,
"min": 0.0005465475932432905,
"max": 0.2728784460002013,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.627383171857138e-06,
"min": 7.627383171857138e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010678336440599993,
"min": 0.00010678336440599993,
"max": 0.0033821777726075,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254242857142858,
"min": 0.10254242857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.435594,
"min": 1.3691136000000002,
"max": 2.5273925,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026398861428571425,
"min": 0.00026398861428571425,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036958405999999995,
"min": 0.0036958405999999995,
"max": 0.11276651075,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.003422623733058572,
"min": 0.003229639260098338,
"max": 0.05684574693441391,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.04791673272848129,
"min": 0.045214951038360596,
"max": 0.3979202210903168,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 478.3333333333333,
"min": 478.3333333333333,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28700.0,
"min": 15984.0,
"max": 34128.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2882866402467092,
"min": -1.0000000521540642,
"max": 1.2882866402467092,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 77.29719841480255,
"min": -32.000001668930054,
"max": 77.29719841480255,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2882866402467092,
"min": -1.0000000521540642,
"max": 1.2882866402467092,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 77.29719841480255,
"min": -32.000001668930054,
"max": 77.29719841480255,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017922177667969663,
"min": 0.017922177667969663,
"max": 4.217124238959514,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.0753306600781798,
"min": 1.0692907293851022,
"max": 67.47398782335222,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712756524",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712758645"
},
"total": 2120.141567365,
"count": 1,
"self": 0.8518361970000115,
"children": {
"run_training.setup": {
"total": 0.050139895000029355,
"count": 1,
"self": 0.050139895000029355
},
"TrainerController.start_learning": {
"total": 2119.239591273,
"count": 1,
"self": 1.285253498145721,
"children": {
"TrainerController._reset_env": {
"total": 2.197649837999961,
"count": 1,
"self": 2.197649837999961
},
"TrainerController.advance": {
"total": 2115.6406735228543,
"count": 63278,
"self": 1.4424337448376718,
"children": {
"env_step": {
"total": 1464.0668370659434,
"count": 63278,
"self": 1333.7164475929924,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.55272434797575,
"count": 63278,
"self": 4.627018743942244,
"children": {
"TorchPolicy.evaluate": {
"total": 124.92570560403351,
"count": 62572,
"self": 124.92570560403351
}
}
},
"workers": {
"total": 0.7976651249753104,
"count": 63278,
"self": 0.0,
"children": {
"worker_root": {
"total": 2114.2824815050235,
"count": 63278,
"is_parallel": true,
"self": 899.6827969010035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002559904000008828,
"count": 1,
"is_parallel": true,
"self": 0.0005895940000755218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019703099999333062,
"count": 8,
"is_parallel": true,
"self": 0.0019703099999333062
}
}
},
"UnityEnvironment.step": {
"total": 0.04654527599996072,
"count": 1,
"is_parallel": true,
"self": 0.0006257620000269526,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004452379998838296,
"count": 1,
"is_parallel": true,
"self": 0.0004452379998838296
},
"communicator.exchange": {
"total": 0.04386807199989562,
"count": 1,
"is_parallel": true,
"self": 0.04386807199989562
},
"steps_from_proto": {
"total": 0.001606204000154321,
"count": 1,
"is_parallel": true,
"self": 0.0003416239999296522,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012645800002246688,
"count": 8,
"is_parallel": true,
"self": 0.0012645800002246688
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.59968460402,
"count": 63277,
"is_parallel": true,
"self": 34.49975784991102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.575846720088293,
"count": 63277,
"is_parallel": true,
"self": 23.575846720088293
},
"communicator.exchange": {
"total": 1058.0026231099052,
"count": 63277,
"is_parallel": true,
"self": 1058.0026231099052
},
"steps_from_proto": {
"total": 98.52145692411545,
"count": 63277,
"is_parallel": true,
"self": 19.57075403045269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.95070289366276,
"count": 506216,
"is_parallel": true,
"self": 78.95070289366276
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 650.1314027120734,
"count": 63278,
"self": 2.317060552104749,
"children": {
"process_trajectory": {
"total": 129.0324917549665,
"count": 63278,
"self": 128.73845035296654,
"children": {
"RLTrainer._checkpoint": {
"total": 0.294041401999948,
"count": 2,
"self": 0.294041401999948
}
}
},
"_update_policy": {
"total": 518.7818504050022,
"count": 429,
"self": 305.6848134569923,
"children": {
"TorchPPOOptimizer.update": {
"total": 213.09703694800987,
"count": 22869,
"self": 213.09703694800987
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.276999682886526e-06,
"count": 1,
"self": 1.276999682886526e-06
},
"TrainerController._save_models": {
"total": 0.1160131370002091,
"count": 1,
"self": 0.0022725570006514317,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11374057999955767,
"count": 1,
"self": 0.11374057999955767
}
}
}
}
}
}
}