Shridipta-06's picture
First Push
f89a841
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3419785797595978,
"min": 0.33380135893821716,
"max": 1.3853479623794556,
"count": 59
},
"Pyramids.Policy.Entropy.sum": {
"value": 10292.1875,
"min": 10028.748046875,
"max": 42025.9140625,
"count": 59
},
"Pyramids.Step.mean": {
"value": 1769940.0,
"min": 29877.0,
"max": 1769940.0,
"count": 59
},
"Pyramids.Step.sum": {
"value": 1769940.0,
"min": 29877.0,
"max": 1769940.0,
"count": 59
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6866150498390198,
"min": -0.1720617413520813,
"max": 0.6930810213088989,
"count": 59
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 196.3719024658203,
"min": -40.77863311767578,
"max": 198.91424560546875,
"count": 59
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.005162531044334173,
"min": -0.008606648072600365,
"max": 0.36684414744377136,
"count": 59
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.4764838218688965,
"min": -2.341008186340332,
"max": 88.40943908691406,
"count": 59
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07132787486366766,
"min": 0.06297397998482923,
"max": 0.07486108388905245,
"count": 59
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9985902480913472,
"min": 0.5240275872233672,
"max": 1.0715498294813701,
"count": 59
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01278921306591513,
"min": 0.00014550997475695936,
"max": 0.015225781570950944,
"count": 59
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17904898292281182,
"min": 0.0018916296718404716,
"max": 0.22176916359846172,
"count": 59
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0001244783585072333,
"min": 0.0001244783585072333,
"max": 0.00029838354339596195,
"count": 59
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0017426970191012662,
"min": 0.0017426970191012662,
"max": 0.0038027494324169332,
"count": 59
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.14149276666666669,
"min": 0.14149276666666669,
"max": 0.19946118095238097,
"count": 59
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.9808987333333337,
"min": 1.3962282666666668,
"max": 2.767583066666667,
"count": 59
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00415512739,
"min": 0.00415512739,
"max": 0.009946171977142856,
"count": 59
},
"Pyramids.Policy.Beta.sum": {
"value": 0.05817178346,
"min": 0.05817178346,
"max": 0.12678154836,
"count": 59
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005134545266628265,
"min": 0.005134545266628265,
"max": 0.5915762782096863,
"count": 59
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07188363373279572,
"min": 0.07188363373279572,
"max": 4.141034126281738,
"count": 59
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 297.95098039215685,
"min": 276.3761467889908,
"max": 999.0,
"count": 59
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30391.0,
"min": 16804.0,
"max": 33161.0,
"count": 59
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6628195947291804,
"min": -0.9999806972280625,
"max": 1.7236238373528927,
"count": 59
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 169.6075986623764,
"min": -31.994001641869545,
"max": 187.8749982714653,
"count": 59
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6628195947291804,
"min": -0.9999806972280625,
"max": 1.7236238373528927,
"count": 59
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 169.6075986623764,
"min": -31.994001641869545,
"max": 187.8749982714653,
"count": 59
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.015921202077936635,
"min": 0.015644068381053866,
"max": 11.460388046853682,
"count": 59
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.623962611949537,
"min": 1.623962611949537,
"max": 194.8265967965126,
"count": 59
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 59
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 59
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687705097",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687709126"
},
"total": 4028.452288126,
"count": 1,
"self": 0.3242844750002405,
"children": {
"run_training.setup": {
"total": 0.0668709530000342,
"count": 1,
"self": 0.0668709530000342
},
"TrainerController.start_learning": {
"total": 4028.0611326979997,
"count": 1,
"self": 2.365291863983657,
"children": {
"TrainerController._reset_env": {
"total": 4.763065915000084,
"count": 1,
"self": 4.763065915000084
},
"TrainerController.advance": {
"total": 4020.7733659540154,
"count": 115293,
"self": 2.465018397806489,
"children": {
"env_step": {
"total": 2914.4301990570425,
"count": 115293,
"self": 2717.3638684679345,
"children": {
"SubprocessEnvManager._take_step": {
"total": 195.59650683607174,
"count": 115293,
"self": 8.48933924817129,
"children": {
"TorchPolicy.evaluate": {
"total": 187.10716758790045,
"count": 111991,
"self": 187.10716758790045
}
}
},
"workers": {
"total": 1.4698237530362803,
"count": 115292,
"self": 0.0,
"children": {
"worker_root": {
"total": 4019.326654646928,
"count": 115292,
"is_parallel": true,
"self": 1503.473515745838,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006060924000053092,
"count": 1,
"is_parallel": true,
"self": 0.00452816699998948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015327570000636115,
"count": 8,
"is_parallel": true,
"self": 0.0015327570000636115
}
}
},
"UnityEnvironment.step": {
"total": 0.047212733999913326,
"count": 1,
"is_parallel": true,
"self": 0.0005797839999104326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004911730000003445,
"count": 1,
"is_parallel": true,
"self": 0.0004911730000003445
},
"communicator.exchange": {
"total": 0.044079643000031865,
"count": 1,
"is_parallel": true,
"self": 0.044079643000031865
},
"steps_from_proto": {
"total": 0.0020621339999706834,
"count": 1,
"is_parallel": true,
"self": 0.0003771799999867653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001684953999983918,
"count": 8,
"is_parallel": true,
"self": 0.001684953999983918
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2515.85313890109,
"count": 115291,
"is_parallel": true,
"self": 60.36819079109546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 40.31301830398991,
"count": 115291,
"is_parallel": true,
"self": 40.31301830398991
},
"communicator.exchange": {
"total": 2233.3262211359975,
"count": 115291,
"is_parallel": true,
"self": 2233.3262211359975
},
"steps_from_proto": {
"total": 181.84570867000718,
"count": 115291,
"is_parallel": true,
"self": 36.13152414936269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 145.7141845206445,
"count": 922328,
"is_parallel": true,
"self": 145.7141845206445
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1103.8781484991666,
"count": 115292,
"self": 4.718901659214453,
"children": {
"process_trajectory": {
"total": 191.3871587039506,
"count": 115292,
"self": 191.08193121895044,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3052274850001595,
"count": 3,
"self": 0.3052274850001595
}
}
},
"_update_policy": {
"total": 907.7720881360017,
"count": 820,
"self": 578.0068813720089,
"children": {
"TorchPPOOptimizer.update": {
"total": 329.76520676399275,
"count": 40842,
"self": 329.76520676399275
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.407000127073843e-06,
"count": 1,
"self": 1.407000127073843e-06
},
"TrainerController._save_models": {
"total": 0.1594075580005665,
"count": 1,
"self": 0.0019338960009918083,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1574736619995747,
"count": 1,
"self": 0.1574736619995747
}
}
}
}
}
}
}