{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8376706838607788, "min": 1.8051265478134155, "max": 3.2957565784454346, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35577.3046875, "min": 19848.62109375, "max": 105464.2109375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.68421052631579, "min": 42.578947368421055, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 16584.0, "max": 23384.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1663.3967316147737, "min": 1196.5979187543865, "max": 1663.3967316147737, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 316045.379006807, "min": 2395.569320642254, "max": 377566.8983084819, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999960.0, "min": 9708.0, "max": 4999960.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999960.0, "min": 9708.0, "max": 4999960.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.04555708169937134, "min": -0.07985325902700424, "max": 0.19135341048240662, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 8.655845642089844, "min": -13.065732955932617, "max": 24.30986976623535, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.046108294278383255, "min": -0.08140623569488525, "max": 0.18512360751628876, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 8.760576248168945, "min": -13.269216537475586, "max": 25.242521286010742, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.10965052654868677, "min": -0.5, "max": 0.6315363564274528, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.83360004425049, "min": -51.719199776649475, "max": 56.63599991798401, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10965052654868677, "min": -0.5, "max": 0.6315363564274528, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.83360004425049, "min": -51.719199776649475, "max": 56.63599991798401, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015534716850379483, "min": 0.01138740125898039, "max": 0.02344134922993059, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015534716850379483, "min": 0.01138740125898039, "max": 0.02344134922993059, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10886789709329606, "min": 0.00028407409142043133, "max": 0.11685129801432291, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10886789709329606, "min": 0.00028407409142043133, "max": 0.11685129801432291, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11038001080354055, "min": 0.00028486197552410884, "max": 0.11863862847288449, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11038001080354055, "min": 0.00028486197552410884, "max": 0.11863862847288449, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689312825", "python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]", "command_line_arguments": "/home/xian/.conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689324849" }, "total": 12023.633325883999, "count": 1, "self": 0.2189660379972338, "children": { "run_training.setup": { "total": 0.00843245900000511, "count": 1, "self": 0.00843245900000511 }, "TrainerController.start_learning": { "total": 12023.405927387, "count": 1, "self": 6.197779051237376, "children": { "TrainerController._reset_env": { "total": 1.9606500649999816, "count": 25, "self": 1.9606500649999816 }, "TrainerController.advance": { "total": 12015.083304923764, "count": 341724, "self": 5.504892749964711, "children": { "env_step": { "total": 3454.3586484649745, "count": 341724, "self": 2793.2794409808585, "children": { "SubprocessEnvManager._take_step": { "total": 657.5875290893117, "count": 341724, "self": 27.470755169439826, "children": { "TorchPolicy.evaluate": { "total": 630.1167739198719, "count": 630728, "self": 630.1167739198719 } } }, "workers": { "total": 3.4916783948044667, "count": 341724, "self": 0.0, "children": { "worker_root": { "total": 12016.400559244681, "count": 341724, "is_parallel": true, "self": 9797.62814296058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002090227999929084, "count": 2, "is_parallel": true, "self": 0.0008736689998158909, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012165590001131932, "count": 8, "is_parallel": true, "self": 0.0012165590001131932 } } }, "UnityEnvironment.step": { "total": 0.015952886999912153, "count": 1, "is_parallel": true, "self": 0.00036837799984823505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033094000002620305, "count": 1, "is_parallel": true, "self": 0.00033094000002620305 }, "communicator.exchange": { "total": 0.014086100999975315, "count": 1, "is_parallel": true, "self": 0.014086100999975315 }, "steps_from_proto": { "total": 0.0011674680000623994, "count": 2, "is_parallel": true, "self": 0.0002462840002408484, "children": { "_process_rank_one_or_two_observation": { "total": 0.000921183999821551, "count": 8, "is_parallel": true, "self": 0.000921183999821551 } } } } } } }, "UnityEnvironment.step": { "total": 2218.742993413103, "count": 341723, "is_parallel": true, "self": 117.69143541927497, "children": { "UnityEnvironment._generate_step_input": { "total": 88.52987714212395, "count": 341723, "is_parallel": true, "self": 88.52987714212395 }, "communicator.exchange": { "total": 1645.593578717394, "count": 341723, "is_parallel": true, "self": 1645.593578717394 }, "steps_from_proto": { "total": 366.92810213430994, "count": 683446, "is_parallel": true, "self": 73.47737806887358, "children": { "_process_rank_one_or_two_observation": { "total": 293.45072406543636, "count": 2733784, "is_parallel": true, "self": 293.45072406543636 } } } } }, "steps_from_proto": { "total": 0.029422870997450445, "count": 48, "is_parallel": true, "self": 0.005983250995086564, "children": { "_process_rank_one_or_two_observation": { "total": 0.02343962000236388, "count": 192, "is_parallel": true, "self": 0.02343962000236388 } } } } } } } } }, "trainer_advance": { "total": 8555.219763708825, "count": 341724, "self": 49.71091876285027, "children": { "process_trajectory": { "total": 997.3751790599687, "count": 341724, "self": 995.7442007559695, "children": { "RLTrainer._checkpoint": { "total": 1.6309783039991999, "count": 10, "self": 1.6309783039991999 } } }, "_update_policy": { "total": 7508.133665886006, "count": 241, "self": 487.66160905802644, "children": { "TorchPOCAOptimizer.update": { "total": 7020.47205682798, "count": 7239, "self": 7020.47205682798 } } } } } } }, "trainer_threads": { "total": 6.399986887117848e-07, "count": 1, "self": 6.399986887117848e-07 }, "TrainerController._save_models": { "total": 0.16419270699952904, "count": 1, "self": 0.0011630279987002723, "children": { "RLTrainer._checkpoint": { "total": 0.16302967900082876, "count": 1, "self": 0.16302967900082876 } } } } } } }