d-ch's picture
SnowballTarget training with ML-Agents
9d1a284 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.28391432762146,
"min": 1.28391432762146,
"max": 2.8785910606384277,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12202.322265625,
"min": 12202.322265625,
"max": 29384.658203125,
"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": 10.828908920288086,
"min": 0.0721384584903717,
"max": 10.828908920288086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2111.63720703125,
"min": 13.994861602783203,
"max": 2145.89404296875,
"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": 23.204545454545453,
"min": 2.8863636363636362,
"max": 23.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1021.0,
"min": 127.0,
"max": 1228.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.204545454545453,
"min": 2.8863636363636362,
"max": 23.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1021.0,
"min": 127.0,
"max": 1228.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.049341693071005915,
"min": 0.04491284351274326,
"max": 0.052547016176486425,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09868338614201183,
"min": 0.08982568702548652,
"max": 0.15334650439520678,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23906604200601578,
"min": 0.0952803146244739,
"max": 0.2939453858370874,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.47813208401203156,
"min": 0.1905606292489478,
"max": 0.8464874663189346,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.432097856000005e-06,
"min": 6.432097856000005e-06,
"max": 0.00029023200325600004,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.286419571200001e-05,
"min": 1.286419571200001e-05,
"max": 0.0007419960526679999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102144,
"min": 0.102144,
"max": 0.196744,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.204288,
"min": 0.204288,
"max": 0.5473320000000002,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.410560000000004e-05,
"min": 7.410560000000004e-05,
"max": 0.0029026456,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00014821120000000008,
"min": 0.00014821120000000008,
"max": 0.0074252268,
"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": "1764884483",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --num-envs=1",
"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": "1764884813"
},
"total": 329.83574796999983,
"count": 1,
"self": 0.3307784389990047,
"children": {
"run_training.setup": {
"total": 0.026542503000200668,
"count": 1,
"self": 0.026542503000200668
},
"TrainerController.start_learning": {
"total": 329.4784270280006,
"count": 1,
"self": 0.28612023196455993,
"children": {
"TrainerController._reset_env": {
"total": 1.9502746600001046,
"count": 1,
"self": 1.9502746600001046
},
"TrainerController.advance": {
"total": 327.1639309290367,
"count": 18192,
"self": 0.31035977396186354,
"children": {
"env_step": {
"total": 244.15411519999816,
"count": 18192,
"self": 182.75028749301146,
"children": {
"SubprocessEnvManager._take_step": {
"total": 61.21495221495843,
"count": 18192,
"self": 1.1124431339649163,
"children": {
"TorchPolicy.evaluate": {
"total": 60.102509080993514,
"count": 18192,
"self": 60.102509080993514
}
}
},
"workers": {
"total": 0.18887549202827358,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 328.6727205889865,
"count": 18192,
"is_parallel": true,
"self": 168.43567093303773,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021244709996608435,
"count": 1,
"is_parallel": true,
"self": 0.0006546489994434523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014698220002173912,
"count": 10,
"is_parallel": true,
"self": 0.0014698220002173912
}
}
},
"UnityEnvironment.step": {
"total": 0.025002246999974886,
"count": 1,
"is_parallel": true,
"self": 0.00036977100080548553,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040305899983650306,
"count": 1,
"is_parallel": true,
"self": 0.00040305899983650306
},
"communicator.exchange": {
"total": 0.02318523899975844,
"count": 1,
"is_parallel": true,
"self": 0.02318523899975844
},
"steps_from_proto": {
"total": 0.0010441779995744582,
"count": 1,
"is_parallel": true,
"self": 0.0002578780004114378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007862999991630204,
"count": 10,
"is_parallel": true,
"self": 0.0007862999991630204
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 160.2370496559488,
"count": 18191,
"is_parallel": true,
"self": 5.955471062094148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.2387703899394182,
"count": 18191,
"is_parallel": true,
"self": 3.2387703899394182
},
"communicator.exchange": {
"total": 132.4498780119793,
"count": 18191,
"is_parallel": true,
"self": 132.4498780119793
},
"steps_from_proto": {
"total": 18.59293019193592,
"count": 18191,
"is_parallel": true,
"self": 3.4770376857140946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.115892506221826,
"count": 181910,
"is_parallel": true,
"self": 15.115892506221826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 82.6994559550767,
"count": 18192,
"self": 0.36434685608855943,
"children": {
"process_trajectory": {
"total": 23.058115056988754,
"count": 18192,
"self": 22.709592106990385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.34852294999836886,
"count": 4,
"self": 0.34852294999836886
}
}
},
"_update_policy": {
"total": 59.27699404199939,
"count": 45,
"self": 32.60204719099511,
"children": {
"TorchPPOOptimizer.update": {
"total": 26.67494685100428,
"count": 2292,
"self": 26.67494685100428
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.829993021208793e-07,
"count": 1,
"self": 8.829993021208793e-07
},
"TrainerController._save_models": {
"total": 0.07810032399993361,
"count": 1,
"self": 0.0007380959996226011,
"children": {
"RLTrainer._checkpoint": {
"total": 0.077362228000311,
"count": 1,
"self": 0.077362228000311
}
}
}
}
}
}
}