LATlag's picture
Trained PPO SnowballTarget agent - Mean Reward 23.5
e6a7f5f verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9775338172912598,
"min": 0.9477811455726624,
"max": 2.8112027645111084,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9290.4814453125,
"min": 9183.783203125,
"max": 28696.7578125,
"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": 11.970306396484375,
"min": 0.406595379114151,
"max": 11.970306396484375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2334.209716796875,
"min": 78.87950134277344,
"max": 2435.68896484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06855507303058117,
"min": 0.05731906517486969,
"max": 0.07619516007766566,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2742202921223247,
"min": 0.22927626069947876,
"max": 0.3809758003883283,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1763604874266129,
"min": 0.1298766901999639,
"max": 0.2770202972725326,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7054419497064516,
"min": 0.5195067607998556,
"max": 1.385101486362663,
"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": 23.545454545454547,
"min": 3.590909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1036.0,
"min": 158.0,
"max": 1287.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.545454545454547,
"min": 3.590909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1036.0,
"min": 158.0,
"max": 1287.0,
"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": "1785061084",
"python_version": "3.10.12 (main, Jun 22 2026, 18:55:27) [GCC 11.4.0]",
"command_line_arguments": "/content/mlagents-env/bin/mlagents-learn ./config/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": "1785061718"
},
"total": 633.7788417710003,
"count": 1,
"self": 0.5423390600003586,
"children": {
"run_training.setup": {
"total": 0.0235366859997157,
"count": 1,
"self": 0.0235366859997157
},
"TrainerController.start_learning": {
"total": 633.2129660250002,
"count": 1,
"self": 0.646517199988466,
"children": {
"TrainerController._reset_env": {
"total": 3.45962035499997,
"count": 1,
"self": 3.45962035499997
},
"TrainerController.advance": {
"total": 629.0093135690117,
"count": 18192,
"self": 0.6645542851160826,
"children": {
"env_step": {
"total": 477.82749916493503,
"count": 18192,
"self": 374.3905378648856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 103.04695958801813,
"count": 18192,
"self": 1.9866459530171596,
"children": {
"TorchPolicy.evaluate": {
"total": 101.06031363500097,
"count": 18192,
"self": 101.06031363500097
}
}
},
"workers": {
"total": 0.39000171203133505,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 629.8201572380126,
"count": 18192,
"is_parallel": true,
"self": 304.68376266801624,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005996015000164334,
"count": 1,
"is_parallel": true,
"self": 0.004231967999203334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017640470009609999,
"count": 10,
"is_parallel": true,
"self": 0.0017640470009609999
}
}
},
"UnityEnvironment.step": {
"total": 0.06952781900008631,
"count": 1,
"is_parallel": true,
"self": 0.0010722290003286616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004767129998981545,
"count": 1,
"is_parallel": true,
"self": 0.0004767129998981545
},
"communicator.exchange": {
"total": 0.06303756099987368,
"count": 1,
"is_parallel": true,
"self": 0.06303756099987368
},
"steps_from_proto": {
"total": 0.004941315999985818,
"count": 1,
"is_parallel": true,
"self": 0.00048483899990969803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00445647700007612,
"count": 10,
"is_parallel": true,
"self": 0.00445647700007612
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 325.13639456999636,
"count": 18191,
"is_parallel": true,
"self": 14.526232018974042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.671621010967101,
"count": 18191,
"is_parallel": true,
"self": 7.671621010967101
},
"communicator.exchange": {
"total": 250.4488187740376,
"count": 18191,
"is_parallel": true,
"self": 250.4488187740376
},
"steps_from_proto": {
"total": 52.48972276601762,
"count": 18191,
"is_parallel": true,
"self": 9.101321949056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.38840081696162,
"count": 181910,
"is_parallel": true,
"self": 43.38840081696162
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 150.51726011896062,
"count": 18192,
"self": 0.8209868179610567,
"children": {
"process_trajectory": {
"total": 31.45944785899792,
"count": 18192,
"self": 30.958805042997938,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5006428159999814,
"count": 4,
"self": 0.5006428159999814
}
}
},
"_update_policy": {
"total": 118.23682544200165,
"count": 90,
"self": 46.42625681502159,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.81056862698006,
"count": 4587,
"self": 71.81056862698006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2069999684172217e-06,
"count": 1,
"self": 1.2069999684172217e-06
},
"TrainerController._save_models": {
"total": 0.09751369400009935,
"count": 1,
"self": 0.0009099839999180404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09660371000018131,
"count": 1,
"self": 0.09660371000018131
}
}
}
}
}
}
}