{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5035665035247803, "min": 1.470587968826294, "max": 3.295746326446533, "count": 1770 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28242.9921875, "min": 27409.775390625, "max": 120267.0, "count": 1770 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.34567901234568, "min": 39.3739837398374, "max": 999.0, "count": 1770 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19552.0, "min": 14212.0, "max": 28212.0, "count": 1770 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1544.5104403214739, "min": 1180.9941894213423, "max": 1603.3526931779911, "count": 1761 }, "SoccerTwos.Self-play.ELO.sum": { "value": 250210.69133207877, "min": 2363.2477491938266, "max": 392660.82324914914, "count": 1761 }, "SoccerTwos.Step.mean": { "value": 17699978.0, "min": 9122.0, "max": 17699978.0, "count": 1770 }, "SoccerTwos.Step.sum": { "value": 17699978.0, "min": 9122.0, "max": 17699978.0, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.028001178056001663, "min": -0.1374976485967636, "max": 0.2069934755563736, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.536190986633301, "min": -28.18701934814453, "max": 27.792827606201172, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.023671336472034454, "min": -0.1340864896774292, "max": 0.2030305713415146, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.834756374359131, "min": -27.168577194213867, "max": 27.650724411010742, "count": 1770 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1770 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07485432021411849, "min": -0.6008615379150097, "max": 0.43080000256030065, "count": 1770 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.126399874687195, "min": -63.243399918079376, "max": 62.33080017566681, "count": 1770 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07485432021411849, "min": -0.6008615379150097, "max": 0.43080000256030065, "count": 1770 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.126399874687195, "min": -63.243399918079376, "max": 62.33080017566681, "count": 1770 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1770 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1770 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013383328518830239, "min": 0.010278040572908745, "max": 0.02610366263737281, "count": 857 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013383328518830239, "min": 0.010278040572908745, "max": 0.02610366263737281, "count": 857 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1036595510939757, "min": 8.419977239100262e-05, "max": 0.12884489769736926, "count": 857 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1036595510939757, "min": 8.419977239100262e-05, "max": 0.12884489769736926, "count": 857 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10672147423028946, "min": 8.521313526822875e-05, "max": 0.13119359935323396, "count": 857 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10672147423028946, "min": 8.521313526822875e-05, "max": 0.13119359935323396, "count": 857 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 857 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 857 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 857 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 857 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 857 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 857 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718514434", "python_version": "3.10.14 (main, Jun 14 2024, 18:23:26) [GCC 11.4.0]", "command_line_arguments": "/home/ivan/Code/rl/hf/unit7/u7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos50M --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718538484" }, "total": 24049.879396452976, "count": 1, "self": 0.0053754179971292615, "children": { "run_training.setup": { "total": 0.011126903991680592, "count": 1, "self": 0.011126903991680592 }, "TrainerController.start_learning": { "total": 24049.862894130987, "count": 1, "self": 19.95134469534969, "children": { "TrainerController._reset_env": { "total": 2.48158151388634, "count": 89, "self": 2.48158151388634 }, "TrainerController.advance": { "total": 24027.216803529765, "count": 1224896, "self": 20.33166449604323, "children": { "env_step": { "total": 17344.032462770992, "count": 1224896, "self": 13189.24239976547, "children": { "SubprocessEnvManager._take_step": { "total": 4141.220234239125, "count": 1224896, "self": 104.04888988181483, "children": { "TorchPolicy.evaluate": { "total": 4037.17134435731, "count": 2225464, "self": 4037.17134435731 } } }, "workers": { "total": 13.569828766398132, "count": 1224895, "self": 0.0, "children": { "worker_root": { "total": 24019.578487852705, "count": 1224895, "is_parallel": true, "self": 13159.66805658117, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00173658796120435, "count": 2, "is_parallel": true, "self": 0.00040872988756746054, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013278580736368895, "count": 8, "is_parallel": true, "self": 0.0013278580736368895 } } }, "UnityEnvironment.step": { "total": 0.018732728029135615, "count": 1, "is_parallel": true, "self": 0.0003881650627590716, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000311177980620414, "count": 1, "is_parallel": true, "self": 0.000311177980620414 }, "communicator.exchange": { "total": 0.01675490802153945, "count": 1, "is_parallel": true, "self": 0.01675490802153945 }, "steps_from_proto": { "total": 0.0012784769642166793, "count": 2, "is_parallel": true, "self": 0.0002583829336799681, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010200940305367112, "count": 8, "is_parallel": true, "self": 0.0010200940305367112 } } } } } } }, "UnityEnvironment.step": { "total": 10859.790246265533, "count": 1224894, "is_parallel": true, "self": 564.7082912233891, "children": { "UnityEnvironment._generate_step_input": { "total": 331.67259040189674, "count": 1224894, "is_parallel": true, "self": 331.67259040189674 }, "communicator.exchange": { "total": 8369.044318542641, "count": 1224894, "is_parallel": true, "self": 8369.044318542641 }, "steps_from_proto": { "total": 1594.365046097606, "count": 2449788, "is_parallel": true, "self": 302.4276817381615, "children": { "_process_rank_one_or_two_observation": { "total": 1291.9373643594445, "count": 9799152, "is_parallel": true, "self": 1291.9373643594445 } } } } }, "steps_from_proto": { "total": 0.12018500600242987, "count": 176, "is_parallel": true, "self": 0.022353325912263244, "children": { "_process_rank_one_or_two_observation": { "total": 0.09783168009016663, "count": 704, "is_parallel": true, "self": 0.09783168009016663 } } } } } } } } }, "trainer_advance": { "total": 6662.85267626273, "count": 1224895, "self": 152.00744313228643, "children": { "process_trajectory": { "total": 2579.932920970081, "count": 1224895, "self": 2573.186581147311, "children": { "RLTrainer._checkpoint": { "total": 6.746339822770096, "count": 35, "self": 6.746339822770096 } } }, "_update_policy": { "total": 3930.9123121603625, "count": 857, "self": 1843.0431646477082, "children": { "TorchPOCAOptimizer.update": { "total": 2087.8691475126543, "count": 25710, "self": 2087.8691475126543 } } } } } } }, "trainer_threads": { "total": 7.069902494549751e-07, "count": 1, "self": 7.069902494549751e-07 }, "TrainerController._save_models": { "total": 0.2131636849953793, "count": 1, "self": 0.000949086039327085, "children": { "RLTrainer._checkpoint": { "total": 0.21221459895605221, "count": 1, "self": 0.21221459895605221 } } } } } } }