ppo-Huggy / run_logs /timers.json
Topofthenod's picture
RL Course Huggy training with unaltered hyperparameters
30f4b68
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4082895517349243,
"min": 1.4082895517349243,
"max": 1.4283841848373413,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71089.046875,
"min": 69400.234375,
"max": 75671.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.56626506024097,
"min": 73.78923766816143,
"max": 406.18548387096774,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49584.0,
"min": 49260.0,
"max": 50367.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999998.0,
"min": 49593.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999998.0,
"min": 49593.0,
"max": 1999998.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.400049924850464,
"min": -0.008008349686861038,
"max": 2.506079912185669,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1195.224853515625,
"min": -0.9770187139511108,
"max": 1640.710205078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.658458121689448,
"min": 1.9253230507745118,
"max": 4.06927930105191,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1821.912144601345,
"min": 234.88941219449043,
"max": 2593.123188138008,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.658458121689448,
"min": 1.9253230507745118,
"max": 4.06927930105191,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1821.912144601345,
"min": 234.88941219449043,
"max": 2593.123188138008,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018393828983729085,
"min": 0.01334685300438044,
"max": 0.020955035622076443,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055181486951187256,
"min": 0.02669370600876088,
"max": 0.055181486951187256,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04728402727180057,
"min": 0.02498480547219515,
"max": 0.06280782675991456,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1418520818154017,
"min": 0.0499696109443903,
"max": 0.18467632954319319,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5473488175833345e-06,
"min": 3.5473488175833345e-06,
"max": 0.000295281226572925,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0642046452750003e-05,
"min": 1.0642046452750003e-05,
"max": 0.00084416506861165,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118241666666666,
"min": 0.10118241666666666,
"max": 0.198427075,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354725,
"min": 0.20761380000000002,
"max": 0.5813883500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.900259166666671e-05,
"min": 6.900259166666671e-05,
"max": 0.004921511042500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020700777500000012,
"min": 0.00020700777500000012,
"max": 0.014071278665000003,
"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": "1696972091",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696976641"
},
"total": 4550.475618324999,
"count": 1,
"self": 0.703714654999203,
"children": {
"run_training.setup": {
"total": 0.06835360100001253,
"count": 1,
"self": 0.06835360100001253
},
"TrainerController.start_learning": {
"total": 4549.703550069,
"count": 1,
"self": 8.7179147192237,
"children": {
"TrainerController._reset_env": {
"total": 1.060523761000013,
"count": 1,
"self": 1.060523761000013
},
"TrainerController.advance": {
"total": 4539.806648957777,
"count": 232827,
"self": 8.791913871789802,
"children": {
"env_step": {
"total": 2862.441346406943,
"count": 232827,
"self": 2399.3870169378197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 457.52774218513355,
"count": 232827,
"self": 30.46612475425286,
"children": {
"TorchPolicy.evaluate": {
"total": 427.0616174308807,
"count": 223127,
"self": 427.0616174308807
}
}
},
"workers": {
"total": 5.526587283989528,
"count": 232827,
"self": 0.0,
"children": {
"worker_root": {
"total": 4535.365509181896,
"count": 232827,
"is_parallel": true,
"self": 2611.50194717994,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012589910000144755,
"count": 1,
"is_parallel": true,
"self": 0.0003712650000124995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000887726000001976,
"count": 2,
"is_parallel": true,
"self": 0.000887726000001976
}
}
},
"UnityEnvironment.step": {
"total": 0.039940495999985615,
"count": 1,
"is_parallel": true,
"self": 0.0004504270000040833,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026092100000596474,
"count": 1,
"is_parallel": true,
"self": 0.00026092100000596474
},
"communicator.exchange": {
"total": 0.038195975999997245,
"count": 1,
"is_parallel": true,
"self": 0.038195975999997245
},
"steps_from_proto": {
"total": 0.0010331719999783218,
"count": 1,
"is_parallel": true,
"self": 0.00030411599996682526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007290560000114965,
"count": 2,
"is_parallel": true,
"self": 0.0007290560000114965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1923.8635620019563,
"count": 232826,
"is_parallel": true,
"self": 60.192265424314655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.94172612486193,
"count": 232826,
"is_parallel": true,
"self": 92.94172612486193
},
"communicator.exchange": {
"total": 1621.1989336478096,
"count": 232826,
"is_parallel": true,
"self": 1621.1989336478096
},
"steps_from_proto": {
"total": 149.53063680497024,
"count": 232826,
"is_parallel": true,
"self": 49.40733984407092,
"children": {
"_process_rank_one_or_two_observation": {
"total": 100.12329696089932,
"count": 465652,
"is_parallel": true,
"self": 100.12329696089932
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1668.573388679044,
"count": 232827,
"self": 12.794686383012504,
"children": {
"process_trajectory": {
"total": 245.78478593403364,
"count": 232827,
"self": 244.5044351940342,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2803507399994487,
"count": 10,
"self": 1.2803507399994487
}
}
},
"_update_policy": {
"total": 1409.993916361998,
"count": 97,
"self": 448.68876859299826,
"children": {
"TorchPPOOptimizer.update": {
"total": 961.3051477689996,
"count": 2910,
"self": 961.3051477689996
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0559997463133186e-06,
"count": 1,
"self": 1.0559997463133186e-06
},
"TrainerController._save_models": {
"total": 0.11846157499985566,
"count": 1,
"self": 0.0054400259996327804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11302154900022288,
"count": 1,
"self": 0.11302154900022288
}
}
}
}
}
}
}