{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7828810214996338, "min": 1.7552826404571533, "max": 3.2957217693328857, "count": 713 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36285.1953125, "min": 10678.6875, "max": 105463.0625, "count": 713 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.88157894736842, "min": 41.47899159663866, "max": 999.0, "count": 713 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19724.0, "min": 16084.0, "max": 23828.0, "count": 713 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1699.968474337901, "min": 1193.3699784199125, "max": 1722.0869812940782, "count": 677 }, "SoccerTwos.Self-play.ELO.sum": { "value": 258395.20809936096, "min": 2386.739956839825, "max": 399045.05954387307, "count": 677 }, "SoccerTwos.Step.mean": { "value": 7129930.0, "min": 9932.0, "max": 7129930.0, "count": 713 }, "SoccerTwos.Step.sum": { "value": 7129930.0, "min": 9932.0, "max": 7129930.0, "count": 713 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006880669388920069, "min": -0.10577674210071564, "max": 0.24683183431625366, "count": 713 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.0458617210388184, "min": -22.42466926574707, "max": 38.164649963378906, "count": 713 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009402930736541748, "min": -0.10187681764364243, "max": 0.25225645303726196, "count": 713 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.4292454719543457, "min": -21.597885131835938, "max": 39.590660095214844, "count": 713 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 713 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 713 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.10632763097160741, "min": -0.663670588942135, "max": 0.7250947387594926, "count": 713 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 16.161799907684326, "min": -71.19319975376129, "max": 81.62080025672913, "count": 713 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10632763097160741, "min": -0.663670588942135, "max": 0.7250947387594926, "count": 713 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 16.161799907684326, "min": -71.19319975376129, "max": 81.62080025672913, "count": 713 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 713 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 713 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022278653418955702, "min": 0.011362400260016633, "max": 0.022300182937760836, "count": 343 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022278653418955702, "min": 0.011362400260016633, "max": 0.022300182937760836, "count": 343 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10393715351819992, "min": 2.155883078103216e-06, "max": 0.12601068566242854, "count": 343 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10393715351819992, "min": 2.155883078103216e-06, "max": 0.12601068566242854, "count": 343 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10601248815655709, "min": 2.7230470777794833e-06, "max": 0.1292967622478803, "count": 343 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10601248815655709, "min": 2.7230470777794833e-06, "max": 0.1292967622478803, "count": 343 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 343 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 343 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 343 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 343 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 343 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 343 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688027583", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/gemcorp/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1688059147" }, "total": 31564.741673506003, "count": 1, "self": 0.12770435200218344, "children": { "run_training.setup": { "total": 0.010024574999988545, "count": 1, "self": 0.010024574999988545 }, "TrainerController.start_learning": { "total": 31564.603944579, "count": 1, "self": 12.704958099413489, "children": { "TrainerController._reset_env": { "total": 2.4719349479837547, "count": 24, "self": 2.4719349479837547 }, "TrainerController.advance": { "total": 31549.030159347596, "count": 485492, "self": 14.360627760848729, "children": { "env_step": { "total": 10562.297803610913, "count": 485492, "self": 8747.939051075024, "children": { "SubprocessEnvManager._take_step": { "total": 1806.5952208288, "count": 485492, "self": 85.33267328216971, "children": { "TorchPolicy.evaluate": { "total": 1721.2625475466302, "count": 897624, "self": 1721.2625475466302 } } }, "workers": { "total": 7.763531707088987, "count": 485491, "self": 0.0, "children": { "worker_root": { "total": 31539.233926992976, "count": 485491, "is_parallel": true, "self": 24257.56701432311, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004239374999087886, "count": 2, "is_parallel": true, "self": 0.0022992490012256894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019401259978621965, "count": 8, "is_parallel": true, "self": 0.0019401259978621965 } } }, "UnityEnvironment.step": { "total": 0.03175384299902362, "count": 1, "is_parallel": true, "self": 0.0019239659995946568, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005734429996664403, "count": 1, "is_parallel": true, "self": 0.0005734429996664403 }, "communicator.exchange": { "total": 0.02603151500079548, "count": 1, "is_parallel": true, "self": 0.02603151500079548 }, "steps_from_proto": { "total": 0.0032249189989670413, "count": 2, "is_parallel": true, "self": 0.00040561000241723377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0028193089965498075, "count": 8, "is_parallel": true, "self": 0.0028193089965498075 } } } } } } }, "UnityEnvironment.step": { "total": 7281.607546317897, "count": 485490, "is_parallel": true, "self": 468.1276119989325, "children": { "UnityEnvironment._generate_step_input": { "total": 337.76952025788705, "count": 485490, "is_parallel": true, "self": 337.76952025788705 }, "communicator.exchange": { "total": 5089.145007864658, "count": 485490, "is_parallel": true, "self": 5089.145007864658 }, "steps_from_proto": { "total": 1386.5654061964196, "count": 970980, "is_parallel": true, "self": 267.8368965601203, "children": { "_process_rank_one_or_two_observation": { "total": 1118.7285096362993, "count": 3883920, "is_parallel": true, "self": 1118.7285096362993 } } } } }, "steps_from_proto": { "total": 0.05936635196849238, "count": 46, "is_parallel": true, "self": 0.011764366980060004, "children": { "_process_rank_one_or_two_observation": { "total": 0.04760198498843238, "count": 184, "is_parallel": true, "self": 0.04760198498843238 } } } } } } } } }, "trainer_advance": { "total": 20972.371727975835, "count": 485491, "self": 89.27485497628732, "children": { "process_trajectory": { "total": 2285.499386999527, "count": 485491, "self": 2280.5551258645264, "children": { "RLTrainer._checkpoint": { "total": 4.944261135000488, "count": 14, "self": 4.944261135000488 } } }, "_update_policy": { "total": 18597.59748600002, "count": 343, "self": 1297.2992455950007, "children": { "TorchPOCAOptimizer.update": { "total": 17300.29824040502, "count": 10290, "self": 17300.29824040502 } } } } } } }, "trainer_threads": { "total": 2.5280023692175746e-06, "count": 1, "self": 2.5280023692175746e-06 }, "TrainerController._save_models": { "total": 0.3968896560036228, "count": 1, "self": 0.002119525001035072, "children": { "RLTrainer._checkpoint": { "total": 0.39477013100258773, "count": 1, "self": 0.39477013100258773 } } } } } } }