ppo-Pyramid / run_logs /timers.json
iblub's picture
First Push
0f023b5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3505159914493561,
"min": 0.3505159914493561,
"max": 1.4629806280136108,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10605.2119140625,
"min": 10605.2119140625,
"max": 44380.98046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5349453091621399,
"min": -0.17311792075634003,
"max": 0.5623140931129456,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 148.1798553466797,
"min": -41.02894592285156,
"max": 155.3626251220703,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.013408168219029903,
"min": 0.011812236160039902,
"max": 0.3545507788658142,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.7140626907348633,
"min": 3.0475568771362305,
"max": 84.02853393554688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06783571474287393,
"min": 0.06478987984398069,
"max": 0.07195037757334691,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9497000064002351,
"min": 0.5036526430134284,
"max": 1.0385305560370859,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015367382812699016,
"min": 0.000558624789001158,
"max": 0.017203818916190543,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21514335937778623,
"min": 0.0072621222570150535,
"max": 0.24085346482666758,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.550133197607142e-06,
"min": 7.550133197607142e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001057018647665,
"min": 0.0001057018647665,
"max": 0.0035083328305558,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251667857142857,
"min": 0.10251667857142857,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352335,
"min": 1.3886848,
"max": 2.5694442000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026141618928571426,
"min": 0.00026141618928571426,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036598266499999997,
"min": 0.0036598266499999997,
"max": 0.11696747558000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01121281087398529,
"min": 0.011075491085648537,
"max": 0.45873603224754333,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15697935223579407,
"min": 0.1550568789243698,
"max": 3.2111523151397705,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.97727272727275,
"min": 326.8988764044944,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30094.0,
"min": 15984.0,
"max": 32892.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5670817994766615,
"min": -1.0000000521540642,
"max": 1.6365557948863783,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 137.9031983539462,
"min": -30.628601729869843,
"max": 140.90419808030128,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5670817994766615,
"min": -1.0000000521540642,
"max": 1.6365557948863783,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 137.9031983539462,
"min": -30.628601729869843,
"max": 140.90419808030128,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04014214497262649,
"min": 0.037671113191566526,
"max": 9.785945247858763,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.532508757591131,
"min": 3.352729074049421,
"max": 156.5751239657402,
"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": "1677410838",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "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": "1.22.4",
"end_time_seconds": "1677413281"
},
"total": 2442.885944783,
"count": 1,
"self": 0.8524476699999468,
"children": {
"run_training.setup": {
"total": 0.12015211600001408,
"count": 1,
"self": 0.12015211600001408
},
"TrainerController.start_learning": {
"total": 2441.913344997,
"count": 1,
"self": 1.3011283539935903,
"children": {
"TrainerController._reset_env": {
"total": 10.600098879,
"count": 1,
"self": 10.600098879
},
"TrainerController.advance": {
"total": 2429.8780165630064,
"count": 63858,
"self": 1.4703579389693004,
"children": {
"env_step": {
"total": 1654.7986338640026,
"count": 63858,
"self": 1541.7832097119108,
"children": {
"SubprocessEnvManager._take_step": {
"total": 112.19918264004545,
"count": 63858,
"self": 4.7220592670129236,
"children": {
"TorchPolicy.evaluate": {
"total": 107.47712337303253,
"count": 62575,
"self": 36.2130888340626,
"children": {
"TorchPolicy.sample_actions": {
"total": 71.26403453896992,
"count": 62575,
"self": 71.26403453896992
}
}
}
}
},
"workers": {
"total": 0.816241512046247,
"count": 63858,
"self": 0.0,
"children": {
"worker_root": {
"total": 2436.5924568170285,
"count": 63858,
"is_parallel": true,
"self": 1011.2636745419918,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006134557999985191,
"count": 1,
"is_parallel": true,
"self": 0.004769444999965344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013651130000198464,
"count": 8,
"is_parallel": true,
"self": 0.0013651130000198464
}
}
},
"UnityEnvironment.step": {
"total": 0.09073503400000504,
"count": 1,
"is_parallel": true,
"self": 0.0005996580000271479,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000506498999982341,
"count": 1,
"is_parallel": true,
"self": 0.000506498999982341
},
"communicator.exchange": {
"total": 0.08632484899999326,
"count": 1,
"is_parallel": true,
"self": 0.08632484899999326
},
"steps_from_proto": {
"total": 0.0033040280000022904,
"count": 1,
"is_parallel": true,
"self": 0.0004844640000101208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028195639999921696,
"count": 8,
"is_parallel": true,
"self": 0.0028195639999921696
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1425.3287822750367,
"count": 63857,
"is_parallel": true,
"self": 33.0230723090408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.039044348015665,
"count": 63857,
"is_parallel": true,
"self": 24.039044348015665
},
"communicator.exchange": {
"total": 1273.6167977929997,
"count": 63857,
"is_parallel": true,
"self": 1273.6167977929997
},
"steps_from_proto": {
"total": 94.64986782498033,
"count": 63857,
"is_parallel": true,
"self": 22.23833521685839,
"children": {
"_process_rank_one_or_two_observation": {
"total": 72.41153260812195,
"count": 510856,
"is_parallel": true,
"self": 72.41153260812195
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 773.6090247600345,
"count": 63858,
"self": 2.4518200970310318,
"children": {
"process_trajectory": {
"total": 167.99499798900374,
"count": 63858,
"self": 167.756125736004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2388722529997267,
"count": 2,
"self": 0.2388722529997267
}
}
},
"_update_policy": {
"total": 603.1622066739997,
"count": 452,
"self": 239.24772629498102,
"children": {
"TorchPPOOptimizer.update": {
"total": 363.91448037901864,
"count": 22821,
"self": 363.91448037901864
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1919996723008808e-06,
"count": 1,
"self": 1.1919996723008808e-06
},
"TrainerController._save_models": {
"total": 0.13410000900012164,
"count": 1,
"self": 0.002417914000034216,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13168209500008743,
"count": 1,
"self": 0.13168209500008743
}
}
}
}
}
}
}