yy1636's picture
Test push
47e488f verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 0.7406678795814514,
"min": 0.2285849153995514,
"max": 3.2957417964935303,
"count": 44
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 19695.83984375,
"min": 3286.95166015625,
"max": 105463.734375,
"count": 44
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 402.09090909090907,
"max": 999.0,
"count": 44
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19980.0,
"min": 9884.0,
"max": 26068.0,
"count": 44
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1201.4048204836322,
"min": 1196.290685250251,
"max": 1202.9980777089495,
"count": 24
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 4805.619281934529,
"min": 2392.581370500502,
"max": 19202.873482256655,
"count": 24
},
"SoccerTwos.Step.mean": {
"value": 439398.0,
"min": 9004.0,
"max": 439398.0,
"count": 44
},
"SoccerTwos.Step.sum": {
"value": 439398.0,
"min": 9004.0,
"max": 439398.0,
"count": 44
},
"SoccerTwos.Policy.ExtrinsicValue.mean": {
"value": 6.75360107421875,
"min": -0.138740673661232,
"max": 14.453667640686035,
"count": 44
},
"SoccerTwos.Policy.ExtrinsicValue.sum": {
"value": 67.5360107421875,
"min": -1.8036288022994995,
"max": 158.99034118652344,
"count": 44
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 44
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 44
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": -0.5710285714428339,
"max": 0.2856266657511393,
"count": 44
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": -7.994400000199676,
"max": 6.373200058937073,
"count": 44
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 44
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 44
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": -20.402108067265242,
"min": -39.199792346486504,
"max": 0.21137248816707155,
"count": 43
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": -20402.108067265242,
"min": -39199.7923464865,
"max": 296.9783458747355,
"count": 43
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0011632326546282558,
"min": 2.6777192233792095e-05,
"max": 0.13458832615434463,
"count": 43
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 1.1632326546282559,
"min": 0.025474487282401523,
"max": 144.27868563745744,
"count": 43
},
"SoccerTwos.Losses.Q1Loss.mean": {
"value": 0.0006108972968629325,
"min": 2.0116678479651647e-05,
"max": 0.23749587374878586,
"count": 43
},
"SoccerTwos.Losses.Q1Loss.sum": {
"value": 0.6108972968629325,
"min": 0.020116678479651647,
"max": 232.22711092036238,
"count": 43
},
"SoccerTwos.Losses.Q2Loss.mean": {
"value": 0.0006352773875940447,
"min": 1.948892518895423e-05,
"max": 0.2372401148256504,
"count": 43
},
"SoccerTwos.Losses.Q2Loss.sum": {
"value": 0.6352773875940447,
"min": 0.01948892518895423,
"max": 233.49981133276793,
"count": 43
},
"SoccerTwos.Policy.DiscreteEntropyCoeff.mean": {
"value": 0.01410618498743628,
"min": 0.0018848056492610154,
"max": 0.117924833656408,
"count": 43
},
"SoccerTwos.Policy.DiscreteEntropyCoeff.sum": {
"value": 14.10618498743628,
"min": 1.769443329400011,
"max": 117.924833656408,
"count": 43
},
"SoccerTwos.Policy.ContinuousEntropyCoeff.mean": {
"value": 0.009999999776482582,
"min": 0.009999999776482582,
"max": 0.009999999776482582,
"count": 43
},
"SoccerTwos.Policy.ContinuousEntropyCoeff.sum": {
"value": 9.999999776482582,
"min": 8.819999802857637,
"max": 14.049999685958028,
"count": 43
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0002999999999999999,
"max": 0.00030000000000000003,
"count": 43
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.3,
"min": 0.2646,
"max": 0.4215,
"count": 43
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713917532",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/robot/anaconda3/envs/rl/bin/mlagents-learn ./config/sac/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-sac--10M --no-graphics",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.22.0",
"end_time_seconds": "1713922126"
},
"total": 4593.2798879110005,
"count": 1,
"self": 0.10645416399984242,
"children": {
"run_training.setup": {
"total": 0.019060461000208306,
"count": 1,
"self": 0.019060461000208306
},
"TrainerController.start_learning": {
"total": 4593.154373286001,
"count": 1,
"self": 0.35967367004013795,
"children": {
"TrainerController._reset_env": {
"total": 1.1065930629988543,
"count": 3,
"self": 1.1065930629988543
},
"TrainerController.advance": {
"total": 4591.5843862949605,
"count": 29319,
"self": 0.38366629686970555,
"children": {
"env_step": {
"total": 341.6344212541085,
"count": 29319,
"self": 252.27588481625162,
"children": {
"SubprocessEnvManager._take_step": {
"total": 89.11158370596104,
"count": 29319,
"self": 2.979635201083056,
"children": {
"TorchPolicy.evaluate": {
"total": 86.13194850487798,
"count": 58172,
"self": 86.13194850487798
}
}
},
"workers": {
"total": 0.24695273189581712,
"count": 29319,
"self": 0.0,
"children": {
"worker_root": {
"total": 4591.6521418511265,
"count": 29319,
"is_parallel": true,
"self": 4387.635103861148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014665650005554198,
"count": 2,
"is_parallel": true,
"self": 0.00033556800008227583,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001130997000473144,
"count": 8,
"is_parallel": true,
"self": 0.001130997000473144
}
}
},
"UnityEnvironment.step": {
"total": 0.017695139000352356,
"count": 1,
"is_parallel": true,
"self": 0.00036204300022291136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025983699970311136,
"count": 1,
"is_parallel": true,
"self": 0.00025983699970311136
},
"communicator.exchange": {
"total": 0.016028946000005817,
"count": 1,
"is_parallel": true,
"self": 0.016028946000005817
},
"steps_from_proto": {
"total": 0.0010443130004205159,
"count": 2,
"is_parallel": true,
"self": 0.00020505300017248373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008392600002480322,
"count": 8,
"is_parallel": true,
"self": 0.0008392600002480322
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.01399128797902,
"count": 29318,
"is_parallel": true,
"self": 11.011533444001998,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.912127386060092,
"count": 29318,
"is_parallel": true,
"self": 6.912127386060092
},
"communicator.exchange": {
"total": 154.96998253492484,
"count": 29318,
"is_parallel": true,
"self": 154.96998253492484
},
"steps_from_proto": {
"total": 31.120347922992096,
"count": 58636,
"is_parallel": true,
"self": 5.771354222930313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.348993700061783,
"count": 234544,
"is_parallel": true,
"self": 25.348993700061783
}
}
}
}
},
"steps_from_proto": {
"total": 0.0030467019987554522,
"count": 4,
"is_parallel": true,
"self": 0.000564296998163627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024824050005918252,
"count": 16,
"is_parallel": true,
"self": 0.0024824050005918252
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 4249.566298743983,
"count": 29319,
"self": 3.468185442945469,
"children": {
"process_trajectory": {
"total": 17.420957824964717,
"count": 29319,
"self": 17.420957824964717
},
"_update_policy": {
"total": 4228.677155476073,
"count": 28317,
"self": 0.5718284660297286,
"children": {
"OffPolicyTrainer._update_policy": {
"total": 4228.105327010043,
"count": 28317,
"self": 3420.2043245720265,
"children": {
"TorchSACOptimizer.update": {
"total": 807.9010024380163,
"count": 43753,
"self": 807.9010024380163
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.380003808066249e-07,
"count": 1,
"self": 7.380003808066249e-07
},
"TrainerController._save_models": {
"total": 0.10371952000059537,
"count": 1,
"self": 0.0010182860005443217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10270123400005104,
"count": 1,
"self": 0.10270123400005104
}
}
}
}
}
}
}