rbpg39's picture
First Push
3ad10ee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8266146779060364,
"min": 0.8171960711479187,
"max": 2.854672431945801,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7856.14599609375,
"min": 7856.14599609375,
"max": 29140.49609375,
"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": 12.182372093200684,
"min": 0.3196202218532562,
"max": 12.182372093200684,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2375.5625,
"min": 62.006324768066406,
"max": 2454.7822265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06196669826578514,
"min": 0.06196669826578514,
"max": 0.07434652467068814,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24786679306314055,
"min": 0.24786679306314055,
"max": 0.3644456663882296,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2126049346783582,
"min": 0.13272019718344524,
"max": 0.2687091777722041,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8504197387134328,
"min": 0.530880788733781,
"max": 1.2465880171341055,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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": 24.022727272727273,
"min": 3.3181818181818183,
"max": 24.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1057.0,
"min": 146.0,
"max": 1321.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.022727272727273,
"min": 3.3181818181818183,
"max": 24.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1057.0,
"min": 146.0,
"max": 1321.0,
"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": "1764035283",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1764035728"
},
"total": 445.808953256,
"count": 1,
"self": 0.43294246899995414,
"children": {
"run_training.setup": {
"total": 0.027169682000021567,
"count": 1,
"self": 0.027169682000021567
},
"TrainerController.start_learning": {
"total": 445.348841105,
"count": 1,
"self": 0.3752215029949184,
"children": {
"TrainerController._reset_env": {
"total": 2.7850810669999646,
"count": 1,
"self": 2.7850810669999646
},
"TrainerController.advance": {
"total": 442.1086224200053,
"count": 18192,
"self": 0.37605091599016305,
"children": {
"env_step": {
"total": 322.4072091390133,
"count": 18192,
"self": 252.01397256902442,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.17280569300351,
"count": 18192,
"self": 1.2396683790072984,
"children": {
"TorchPolicy.evaluate": {
"total": 68.93313731399621,
"count": 18192,
"self": 68.93313731399621
}
}
},
"workers": {
"total": 0.2204308769853469,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.49328388899016,
"count": 18192,
"is_parallel": true,
"self": 221.88662858499288,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006474119999893446,
"count": 1,
"is_parallel": true,
"self": 0.004540478000080839,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019336419998126075,
"count": 10,
"is_parallel": true,
"self": 0.0019336419998126075
}
}
},
"UnityEnvironment.step": {
"total": 0.03618339200011178,
"count": 1,
"is_parallel": true,
"self": 0.000613090000115335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042096000015590107,
"count": 1,
"is_parallel": true,
"self": 0.00042096000015590107
},
"communicator.exchange": {
"total": 0.03305039199995008,
"count": 1,
"is_parallel": true,
"self": 0.03305039199995008
},
"steps_from_proto": {
"total": 0.002098949999890465,
"count": 1,
"is_parallel": true,
"self": 0.0003751950002879312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017237549996025336,
"count": 10,
"is_parallel": true,
"self": 0.0017237549996025336
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.6066553039973,
"count": 18191,
"is_parallel": true,
"self": 10.612982713007796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.466216300005954,
"count": 18191,
"is_parallel": true,
"self": 5.466216300005954
},
"communicator.exchange": {
"total": 168.5043745549949,
"count": 18191,
"is_parallel": true,
"self": 168.5043745549949
},
"steps_from_proto": {
"total": 37.023081735988626,
"count": 18191,
"is_parallel": true,
"self": 6.7230243439692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.300057392019426,
"count": 181910,
"is_parallel": true,
"self": 30.300057392019426
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.32536236500187,
"count": 18192,
"self": 0.45964149700193957,
"children": {
"process_trajectory": {
"total": 26.647251894998362,
"count": 18192,
"self": 26.090639293998265,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5566126010000971,
"count": 4,
"self": 0.5566126010000971
}
}
},
"_update_policy": {
"total": 92.21846897300156,
"count": 90,
"self": 37.59297911501312,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.62548985798844,
"count": 4587,
"self": 54.62548985798844
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1269999049545731e-06,
"count": 1,
"self": 1.1269999049545731e-06
},
"TrainerController._save_models": {
"total": 0.07991498799992769,
"count": 1,
"self": 0.0007296280000446131,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07918535999988308,
"count": 1,
"self": 0.07918535999988308
}
}
}
}
}
}
}