{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.292132616043091, "min": 2.2572052478790283, "max": 3.2958037853240967, "count": 1126 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46869.52734375, "min": 8051.8291015625, "max": 161575.640625, "count": 1126 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.784946236559136, "min": 39.47154471544715, "max": 999.0, "count": 1126 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19636.0, "min": 12904.0, "max": 27260.0, "count": 1126 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1540.1519592437812, "min": 1181.6775315885016, "max": 1549.7725386332547, "count": 1008 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286468.2644193433, "min": 2363.355063177003, "max": 350163.47599503293, "count": 1008 }, "SoccerTwos.Step.mean": { "value": 11259942.0, "min": 9648.0, "max": 11259942.0, "count": 1126 }, "SoccerTwos.Step.sum": { "value": 11259942.0, "min": 9648.0, "max": 11259942.0, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02175154536962509, "min": -0.08181066811084747, "max": 0.16583144664764404, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.045787334442139, "min": -14.971351623535156, "max": 21.337879180908203, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.021867506206035614, "min": -0.0818493589758873, "max": 0.16594870388507843, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.067356109619141, "min": -15.960625648498535, "max": 21.526124954223633, "count": 1126 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1126 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03914623683498752, "min": -0.6153846153846154, "max": 0.41731489085136575, "count": 1126 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.281200051307678, "min": -52.95340007543564, "max": 59.68079996109009, "count": 1126 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03914623683498752, "min": -0.6153846153846154, "max": 0.41731489085136575, "count": 1126 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.281200051307678, "min": -52.95340007543564, "max": 59.68079996109009, "count": 1126 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1126 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1126 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015966420065403022, "min": 0.009779906947126922, "max": 0.025029756675940006, "count": 533 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015966420065403022, "min": 0.009779906947126922, "max": 0.025029756675940006, "count": 533 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07688813060522079, "min": 3.8149103147588904e-07, "max": 0.08983085478345552, "count": 533 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07688813060522079, "min": 3.8149103147588904e-07, "max": 0.08983085478345552, "count": 533 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07765562906861305, "min": 5.127459023886634e-07, "max": 0.09085923979679743, "count": 533 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07765562906861305, "min": 5.127459023886634e-07, "max": 0.09085923979679743, "count": 533 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 533 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 533 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.17999999999999997, "min": 0.17999999999999997, "max": 0.17999999999999997, "count": 533 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.17999999999999997, "min": 0.17999999999999997, "max": 0.17999999999999997, "count": 533 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.007000000000000002, "min": 0.007000000000000002, "max": 0.007000000000000002, "count": 533 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.007000000000000002, "min": 0.007000000000000002, "max": 0.007000000000000002, "count": 533 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675421136", "python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]", "command_line_arguments": "/home/rere/miniconda3/envs/rl/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos_01 --no-graphics --torch-device cuda:0", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675439443" }, "total": 18306.663035994003, "count": 1, "self": 0.9977862580017245, "children": { "run_training.setup": { "total": 0.007945340999867767, "count": 1, "self": 0.007945340999867767 }, "TrainerController.start_learning": { "total": 18305.657304395, "count": 1, "self": 15.374812116697285, "children": { "TrainerController._reset_env": { "total": 9.146132168985787, "count": 57, "self": 9.146132168985787 }, "TrainerController.advance": { "total": 18281.01684047932, "count": 751722, "self": 16.552055113919778, "children": { "env_step": { "total": 14103.620230038265, "count": 751722, "self": 11001.98278670678, "children": { "SubprocessEnvManager._take_step": { "total": 3092.02788804421, "count": 751722, "self": 94.30382046052819, "children": { "TorchPolicy.evaluate": { "total": 2997.724067583682, "count": 1439398, "self": 2997.724067583682 } } }, "workers": { "total": 9.609555287273906, "count": 751721, "self": 0.0, "children": { "worker_root": { "total": 18282.71187319878, "count": 751721, "is_parallel": true, "self": 9090.156762385635, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002979571000651049, "count": 2, "is_parallel": true, "self": 0.0013245250020190724, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016550459986319765, "count": 8, "is_parallel": true, "self": 0.0016550459986319765 } } }, "UnityEnvironment.step": { "total": 0.023795369999788818, "count": 1, "is_parallel": true, "self": 0.0004765539988511591, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040580000040790765, "count": 1, "is_parallel": true, "self": 0.00040580000040790765 }, "communicator.exchange": { "total": 0.021398771999884048, "count": 1, "is_parallel": true, "self": 0.021398771999884048 }, "steps_from_proto": { "total": 0.0015142440006457036, "count": 2, "is_parallel": true, "self": 0.0003207240006304346, "children": { "_process_rank_one_or_two_observation": { "total": 0.001193520000015269, "count": 8, "is_parallel": true, "self": 0.001193520000015269 } } } } } } }, "UnityEnvironment.step": { "total": 9192.44553035613, "count": 751720, "is_parallel": true, "self": 572.807218609305, "children": { "UnityEnvironment._generate_step_input": { "total": 322.06720877933185, "count": 751720, "is_parallel": true, "self": 322.06720877933185 }, "communicator.exchange": { "total": 6728.8590341110075, "count": 751720, "is_parallel": true, "self": 6728.8590341110075 }, "steps_from_proto": { "total": 1568.7120688564864, "count": 1503440, "is_parallel": true, "self": 261.1362915857608, "children": { "_process_rank_one_or_two_observation": { "total": 1307.5757772707257, "count": 6013760, "is_parallel": true, "self": 1307.5757772707257 } } } } }, "steps_from_proto": { "total": 0.10958045701499941, "count": 112, "is_parallel": true, "self": 0.01811771900520398, "children": { "_process_rank_one_or_two_observation": { "total": 0.09146273800979543, "count": 448, "is_parallel": true, "self": 0.09146273800979543 } } } } } } } } }, "trainer_advance": { "total": 4160.844555327133, "count": 751721, "self": 101.44228592397576, "children": { "process_trajectory": { "total": 1276.6872187961626, "count": 751721, "self": 1273.6160992441573, "children": { "RLTrainer._checkpoint": { "total": 3.071119552005257, "count": 22, "self": 3.071119552005257 } } }, "_update_policy": { "total": 2782.7150506069947, "count": 534, "self": 1481.6673787659538, "children": { "TorchPOCAOptimizer.update": { "total": 1301.047671841041, "count": 16020, "self": 1301.047671841041 } } } } } } }, "trainer_threads": { "total": 7.779999577905983e-07, "count": 1, "self": 7.779999577905983e-07 }, "TrainerController._save_models": { "total": 0.11951885199960088, "count": 1, "self": 0.0011729610014299396, "children": { "RLTrainer._checkpoint": { "total": 0.11834589099817094, "count": 1, "self": 0.11834589099817094 } } } } } } }