|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.5445958375930786, |
|
"min": 1.5416514873504639, |
|
"max": 1.54746413230896, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 32226.447265625, |
|
"min": 29254.37890625, |
|
"max": 32979.5546875, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 54.31111111111111, |
|
"min": 54.23076923076923, |
|
"max": 55.325301204819276, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19552.0, |
|
"min": 18368.0, |
|
"max": 19740.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1571.8056838183572, |
|
"min": 1568.214947912237, |
|
"max": 1571.8056838183572, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 282925.0230873043, |
|
"min": 260370.00044767454, |
|
"max": 285415.1205200271, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 28149988.0, |
|
"min": 28129767.0, |
|
"max": 28149988.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 28149988.0, |
|
"min": 28129767.0, |
|
"max": 28149988.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.04595968499779701, |
|
"min": -0.06847310066223145, |
|
"max": -0.02722092904150486, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -8.318702697753906, |
|
"min": -11.29806137084961, |
|
"max": -4.926988124847412, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.044073380529880524, |
|
"min": -0.06511271744966507, |
|
"max": -0.02285114862024784, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -7.97728157043457, |
|
"min": -10.743598937988281, |
|
"max": -4.1360578536987305, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.09876685182033981, |
|
"min": -0.15006303064750903, |
|
"max": -0.014512706198086396, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -17.876800179481506, |
|
"min": -24.76040005683899, |
|
"max": -2.6267998218536377, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.09876685182033981, |
|
"min": -0.15006303064750903, |
|
"max": -0.014512706198086396, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -17.876800179481506, |
|
"min": -24.76040005683899, |
|
"max": -2.6267998218536377, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.01899477666399131, |
|
"min": 0.01899477666399131, |
|
"max": 0.01899477666399131, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01899477666399131, |
|
"min": 0.01899477666399131, |
|
"max": 0.01899477666399131, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10417718564470609, |
|
"min": 0.10417718564470609, |
|
"max": 0.10417718564470609, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10417718564470609, |
|
"min": 0.10417718564470609, |
|
"max": 0.10417718564470609, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.10623087485631307, |
|
"min": 0.10623087485631307, |
|
"max": 0.10623087485631307, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.10623087485631307, |
|
"min": 0.10623087485631307, |
|
"max": 0.10623087485631307, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 1 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 1 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1713812627", |
|
"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 /home/robot/ml-agents/config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-test-0 --resume", |
|
"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": "1713812666" |
|
}, |
|
"total": 39.1336410240001, |
|
"count": 1, |
|
"self": 0.07609515899912367, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.018059835000713065, |
|
"count": 1, |
|
"self": 0.018059835000713065 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 39.03948603000026, |
|
"count": 1, |
|
"self": 0.033418846981476236, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.6074643390002166, |
|
"count": 2, |
|
"self": 3.6074643390002166 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 35.256843977018434, |
|
"count": 2454, |
|
"self": 0.03523478700208216, |
|
"children": { |
|
"env_step": { |
|
"total": 27.403868124021756, |
|
"count": 2454, |
|
"self": 20.012116775008508, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 7.371224686995447, |
|
"count": 2454, |
|
"self": 0.1943202859856683, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 7.176904401009779, |
|
"count": 4414, |
|
"self": 7.176904401009779 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.020526662017800845, |
|
"count": 2454, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 38.87065808505031, |
|
"count": 2454, |
|
"is_parallel": true, |
|
"self": 22.53269678203833, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001703715999610722, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00040343199907511007, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001300284000535612, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001300284000535612 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.01667100000031496, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006059349998395192, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00026192299992544577, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00026192299992544577 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.013998334999996587, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.013998334999996587 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.00180480700055341, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00033896400145749794, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001465842999095912, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001465842999095912 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011036900004910422, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.00020813900118810125, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008955509993029409, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008955509993029409 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 16.33685761301149, |
|
"count": 2453, |
|
"is_parallel": true, |
|
"self": 0.8624507790482312, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.5040812960078256, |
|
"count": 2453, |
|
"is_parallel": true, |
|
"self": 0.5040812960078256 |
|
}, |
|
"communicator.exchange": { |
|
"total": 12.556463673989128, |
|
"count": 2453, |
|
"is_parallel": true, |
|
"self": 12.556463673989128 |
|
}, |
|
"steps_from_proto": { |
|
"total": 2.4138618639663036, |
|
"count": 4906, |
|
"is_parallel": true, |
|
"self": 0.45623346995762404, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 1.9576283940086796, |
|
"count": 19624, |
|
"is_parallel": true, |
|
"self": 1.9576283940086796 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 7.817741065994596, |
|
"count": 2453, |
|
"self": 0.20603566197860346, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 4.2107163620157735, |
|
"count": 2453, |
|
"self": 4.2107163620157735 |
|
}, |
|
"_update_policy": { |
|
"total": 3.4009890420002193, |
|
"count": 1, |
|
"self": 1.9541460469990852, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 1.4468429950011341, |
|
"count": 30, |
|
"self": 1.4468429950011341 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 5.869997039553709e-07, |
|
"count": 1, |
|
"self": 5.869997039553709e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1417582800004311, |
|
"count": 1, |
|
"self": 0.0010400099999969825, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14071827000043413, |
|
"count": 1, |
|
"self": 0.14071827000043413 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |