Adi-AI-2005's picture
First Push of snowball target
1bd4920 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7546176910400391,
"min": 0.7546176910400391,
"max": 2.8328897953033447,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7171.88671875,
"min": 7171.88671875,
"max": 28918.138671875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.194284439086914,
"min": 0.47482243180274963,
"max": 13.194284439086914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2572.885498046875,
"min": 91.64073181152344,
"max": 2662.864501953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06122171819865174,
"min": 0.06060513433699003,
"max": 0.07355038587839396,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24488687279460697,
"min": 0.24488687279460697,
"max": 0.34925092449503053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20844674000845237,
"min": 0.1403845646715376,
"max": 0.3106825807515312,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8337869600338095,
"min": 0.5615382586861504,
"max": 1.553412903757656,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.98609733800001e-06,
"min": 7.98609733800001e-06,
"max": 0.00029178600273799997,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.194438935200004e-05,
"min": 3.194438935200004e-05,
"max": 0.00138468003844,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102662,
"min": 0.102662,
"max": 0.19726200000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410648,
"min": 0.410648,
"max": 0.96156,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014283380000000017,
"min": 0.00014283380000000017,
"max": 0.0048633738,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005713352000000007,
"min": 0.0005713352000000007,
"max": 0.023081844,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.90909090909091,
"min": 3.727272727272727,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 164.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.727272727272727,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 164.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1736782376",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736782808"
},
"total": 432.16650479400005,
"count": 1,
"self": 0.4743618450000895,
"children": {
"run_training.setup": {
"total": 0.057771690999970815,
"count": 1,
"self": 0.057771690999970815
},
"TrainerController.start_learning": {
"total": 431.634371258,
"count": 1,
"self": 0.3787275690001479,
"children": {
"TrainerController._reset_env": {
"total": 1.9777884129999848,
"count": 1,
"self": 1.9777884129999848
},
"TrainerController.advance": {
"total": 429.18998525999984,
"count": 18192,
"self": 0.37648035299935145,
"children": {
"env_step": {
"total": 306.3215845119962,
"count": 18192,
"self": 233.10862541099993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.9876464780092,
"count": 18192,
"self": 1.2878025630092225,
"children": {
"TorchPolicy.evaluate": {
"total": 71.69984391499997,
"count": 18192,
"self": 71.69984391499997
}
}
},
"workers": {
"total": 0.22531262298707588,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.16990796499977,
"count": 18192,
"is_parallel": true,
"self": 226.57376632099852,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022239759999820308,
"count": 1,
"is_parallel": true,
"self": 0.0006810939996739762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015428820003080546,
"count": 10,
"is_parallel": true,
"self": 0.0015428820003080546
}
}
},
"UnityEnvironment.step": {
"total": 0.03770568400000229,
"count": 1,
"is_parallel": true,
"self": 0.00067788000001201,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004144380000070669,
"count": 1,
"is_parallel": true,
"self": 0.0004144380000070669
},
"communicator.exchange": {
"total": 0.03452157599997463,
"count": 1,
"is_parallel": true,
"self": 0.03452157599997463
},
"steps_from_proto": {
"total": 0.0020917900000085865,
"count": 1,
"is_parallel": true,
"self": 0.00039184700005989725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016999429999486892,
"count": 10,
"is_parallel": true,
"self": 0.0016999429999486892
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.59614164400125,
"count": 18191,
"is_parallel": true,
"self": 10.105885634004494,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.568592300998375,
"count": 18191,
"is_parallel": true,
"self": 5.568592300998375
},
"communicator.exchange": {
"total": 154.8583324270005,
"count": 18191,
"is_parallel": true,
"self": 154.8583324270005
},
"steps_from_proto": {
"total": 33.063331281997876,
"count": 18191,
"is_parallel": true,
"self": 5.929838574992914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.13349270700496,
"count": 181910,
"is_parallel": true,
"self": 27.13349270700496
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.49192039500429,
"count": 18192,
"self": 0.4571976820010377,
"children": {
"process_trajectory": {
"total": 28.100970442003018,
"count": 18192,
"self": 27.666881266002974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43408917600004315,
"count": 4,
"self": 0.43408917600004315
}
}
},
"_update_policy": {
"total": 93.93375227100023,
"count": 90,
"self": 38.22891458500112,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.70483768599911,
"count": 4587,
"self": 55.70483768599911
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0290000318491366e-06,
"count": 1,
"self": 1.0290000318491366e-06
},
"TrainerController._save_models": {
"total": 0.08786898699997892,
"count": 1,
"self": 0.0011401719999639681,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08672881500001495,
"count": 1,
"self": 0.08672881500001495
}
}
}
}
}
}
}