PyramidsRND / run_logs /timers.json
ElementBrawler's picture
First training for PyramidRND
bb81697
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8167691230773926,
"min": 0.8167691230773926,
"max": 1.452033519744873,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 24463.869140625,
"min": 24463.869140625,
"max": 44048.890625,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89943.0,
"min": 29952.0,
"max": 89943.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89943.0,
"min": 29952.0,
"max": 89943.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.09244344383478165,
"min": -0.10529731214046478,
"max": -0.09244344383478165,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -22.186426162719727,
"min": -24.955463409423828,
"max": -22.186426162719727,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.1690806895494461,
"min": 0.16874651610851288,
"max": 0.25449445843696594,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 40.57936477661133,
"min": 39.992923736572266,
"max": 61.33316421508789,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06830564729005183,
"min": 0.06830564729005183,
"max": 0.0721332325220352,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.6147508256104665,
"min": 0.5049326276542464,
"max": 0.6447482374010963,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0002378650806171975,
"min": 0.0002378650806171975,
"max": 0.006066062268878333,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0021407857255547774,
"min": 0.0021407857255547774,
"max": 0.04246243588214833,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.475240841588888e-05,
"min": 7.475240841588888e-05,
"max": 0.0002515063018788571,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0006727716757429999,
"min": 0.0006727716757429999,
"max": 0.0017605441131519997,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12491744444444447,
"min": 0.12491744444444447,
"max": 0.1838354285714286,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.1242570000000003,
"min": 1.1242570000000003,
"max": 1.38635,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0024992527000000002,
"min": 0.0024992527000000002,
"max": 0.008385159314285713,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0224932743,
"min": 0.0224932743,
"max": 0.058696115199999996,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.10023115575313568,
"min": 0.10023115575313568,
"max": 0.3753523826599121,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.9020804166793823,
"min": 0.9020804166793823,
"max": 2.6274666786193848,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 986.8484848484849,
"max": 999.0,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31968.0,
"min": 15984.0,
"max": 32566.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -0.9272121714823174,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -0.9272121714823174,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -32.000001668930054,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.1914042222779244,
"min": 1.1914042222779244,
"max": 7.563053228892386,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 38.12493511289358,
"min": 38.12493511289358,
"max": 121.00885166227818,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679464280",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679464475"
},
"total": 194.77187541000012,
"count": 1,
"self": 0.7457656650001354,
"children": {
"run_training.setup": {
"total": 0.10276488299996345,
"count": 1,
"self": 0.10276488299996345
},
"TrainerController.start_learning": {
"total": 193.92334486200002,
"count": 1,
"self": 0.1460976430021219,
"children": {
"TrainerController._reset_env": {
"total": 7.096231325999952,
"count": 1,
"self": 7.096231325999952
},
"TrainerController.advance": {
"total": 186.5140350829979,
"count": 6256,
"self": 0.145697865999864,
"children": {
"env_step": {
"total": 122.86093506799784,
"count": 6256,
"self": 111.49307102498847,
"children": {
"SubprocessEnvManager._take_step": {
"total": 11.28470693700774,
"count": 6256,
"self": 0.46258730100907997,
"children": {
"TorchPolicy.evaluate": {
"total": 10.82211963599866,
"count": 6256,
"self": 10.82211963599866
}
}
},
"workers": {
"total": 0.08315710600163584,
"count": 6256,
"self": 0.0,
"children": {
"worker_root": {
"total": 193.0190538669999,
"count": 6256,
"is_parallel": true,
"self": 92.52163129399855,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017337829999632959,
"count": 1,
"is_parallel": true,
"self": 0.00057002599965017,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001163757000313126,
"count": 8,
"is_parallel": true,
"self": 0.001163757000313126
}
}
},
"UnityEnvironment.step": {
"total": 0.046447873999795775,
"count": 1,
"is_parallel": true,
"self": 0.0005278359999465465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004309050000301795,
"count": 1,
"is_parallel": true,
"self": 0.0004309050000301795
},
"communicator.exchange": {
"total": 0.0435790009998982,
"count": 1,
"is_parallel": true,
"self": 0.0435790009998982
},
"steps_from_proto": {
"total": 0.00191013199992085,
"count": 1,
"is_parallel": true,
"self": 0.0003737609999916458,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015363709999292041,
"count": 8,
"is_parallel": true,
"self": 0.0015363709999292041
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 100.49742257300136,
"count": 6255,
"is_parallel": true,
"self": 3.072848388999546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.257832362995032,
"count": 6255,
"is_parallel": true,
"self": 2.257832362995032
},
"communicator.exchange": {
"total": 86.17355633900547,
"count": 6255,
"is_parallel": true,
"self": 86.17355633900547
},
"steps_from_proto": {
"total": 8.993185482001309,
"count": 6255,
"is_parallel": true,
"self": 1.9547386239839852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.038446858017323,
"count": 50040,
"is_parallel": true,
"self": 7.038446858017323
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 63.5074021490002,
"count": 6256,
"self": 0.2029007779967742,
"children": {
"process_trajectory": {
"total": 11.347182169003645,
"count": 6256,
"self": 11.347182169003645
},
"_update_policy": {
"total": 51.95731920199978,
"count": 28,
"self": 33.21267860700118,
"children": {
"TorchPPOOptimizer.update": {
"total": 18.7446405949986,
"count": 2286,
"self": 18.7446405949986
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2230000265844865e-06,
"count": 1,
"self": 1.2230000265844865e-06
},
"TrainerController._save_models": {
"total": 0.16697958700001436,
"count": 1,
"self": 0.00206316899993908,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16491641800007528,
"count": 1,
"self": 0.16491641800007528
}
}
}
}
}
}
}