sauravdas101's picture
First Push
77e4653 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8739539980888367,
"min": 0.8739539980888367,
"max": 2.8686330318450928,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8306.05859375,
"min": 8306.05859375,
"max": 29283.005859375,
"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": 13.238754272460938,
"min": 0.4071054458618164,
"max": 13.238754272460938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2581.55712890625,
"min": 78.97845458984375,
"max": 2683.412109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07068280360716231,
"min": 0.06367871221668525,
"max": 0.07647364672462287,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28273121442864924,
"min": 0.2610539155210455,
"max": 0.36266126900833723,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18351298176190434,
"min": 0.11143658346469132,
"max": 0.27849120784039594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7340519270476173,
"min": 0.4457463338587653,
"max": 1.3924560392019796,
"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": 25.545454545454547,
"min": 3.090909090909091,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 136.0,
"max": 1445.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.090909090909091,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 136.0,
"max": 1445.0,
"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": "1754683296",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --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": "1754683707"
},
"total": 411.1634126790001,
"count": 1,
"self": 0.43619515700004285,
"children": {
"run_training.setup": {
"total": 0.022405494000054205,
"count": 1,
"self": 0.022405494000054205
},
"TrainerController.start_learning": {
"total": 410.704812028,
"count": 1,
"self": 0.3219785269982367,
"children": {
"TrainerController._reset_env": {
"total": 3.0794591950000267,
"count": 1,
"self": 3.0794591950000267
},
"TrainerController.advance": {
"total": 407.2267011470018,
"count": 18192,
"self": 0.3540745390311031,
"children": {
"env_step": {
"total": 288.08921217498414,
"count": 18192,
"self": 221.85937717797844,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.02050642699271,
"count": 18192,
"self": 1.217223945978617,
"children": {
"TorchPolicy.evaluate": {
"total": 64.8032824810141,
"count": 18192,
"self": 64.8032824810141
}
}
},
"workers": {
"total": 0.20932857001298544,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 409.48067284801266,
"count": 18192,
"is_parallel": true,
"self": 214.35344394501954,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007390850999968279,
"count": 1,
"is_parallel": true,
"self": 0.005198797999810267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002192053000158012,
"count": 10,
"is_parallel": true,
"self": 0.002192053000158012
}
}
},
"UnityEnvironment.step": {
"total": 0.03425112000002173,
"count": 1,
"is_parallel": true,
"self": 0.0005486949997930424,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004060700000536599,
"count": 1,
"is_parallel": true,
"self": 0.0004060700000536599
},
"communicator.exchange": {
"total": 0.031525517000090986,
"count": 1,
"is_parallel": true,
"self": 0.031525517000090986
},
"steps_from_proto": {
"total": 0.0017708380000840407,
"count": 1,
"is_parallel": true,
"self": 0.00033790400004818366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001432934000035857,
"count": 10,
"is_parallel": true,
"self": 0.001432934000035857
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.12722890299312,
"count": 18191,
"is_parallel": true,
"self": 9.53977515196948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.193479857006423,
"count": 18191,
"is_parallel": true,
"self": 5.193479857006423
},
"communicator.exchange": {
"total": 149.67038444500838,
"count": 18191,
"is_parallel": true,
"self": 149.67038444500838
},
"steps_from_proto": {
"total": 30.72358944900884,
"count": 18191,
"is_parallel": true,
"self": 5.44697550904948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.27661393995936,
"count": 181910,
"is_parallel": true,
"self": 25.27661393995936
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.78341443298655,
"count": 18192,
"self": 0.38705834898235025,
"children": {
"process_trajectory": {
"total": 26.155038428004218,
"count": 18192,
"self": 25.63228108700423,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5227573409999877,
"count": 4,
"self": 0.5227573409999877
}
}
},
"_update_policy": {
"total": 92.24131765599998,
"count": 90,
"self": 37.797637277999456,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.44368037800052,
"count": 4587,
"self": 54.44368037800052
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.309999313700246e-07,
"count": 1,
"self": 9.309999313700246e-07
},
"TrainerController._save_models": {
"total": 0.07667222800000673,
"count": 1,
"self": 0.0008003930001905246,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0758718349998162,
"count": 1,
"self": 0.0758718349998162
}
}
}
}
}
}
}