| { | |
| "name": "root", | |
| "gauges": { | |
| "SoccerTwos.Policy.Entropy.mean": { | |
| "value": 1.7008748054504395, | |
| "min": 1.663567304611206, | |
| "max": 3.215458869934082, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.Entropy.sum": { | |
| "value": 35378.1953125, | |
| "min": 3601.31396484375, | |
| "max": 109269.09375, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.mean": { | |
| "value": 61.25925925925926, | |
| "min": 33.0, | |
| "max": 999.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.EpisodeLength.sum": { | |
| "value": 19848.0, | |
| "min": 132.0, | |
| "max": 23604.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Self-play.ELO.mean": { | |
| "value": 1601.063072405119, | |
| "min": 1186.2999109760294, | |
| "max": 1624.7476819538674, | |
| "count": 850 | |
| }, | |
| "SoccerTwos.Self-play.ELO.sum": { | |
| "value": 259372.21772962928, | |
| "min": 2377.0248932028644, | |
| "max": 346340.74750691757, | |
| "count": 850 | |
| }, | |
| "SoccerTwos.Step.mean": { | |
| "value": 9999910.0, | |
| "min": 1499980.0, | |
| "max": 9999910.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Step.sum": { | |
| "value": 9999910.0, | |
| "min": 1499980.0, | |
| "max": 9999910.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { | |
| "value": -0.038446467369794846, | |
| "min": -0.11436130851507187, | |
| "max": 0.16732440888881683, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { | |
| "value": -6.189881324768066, | |
| "min": -21.297691345214844, | |
| "max": 20.255615234375, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.037617385387420654, | |
| "min": -0.11490459740161896, | |
| "max": 0.1676502525806427, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -6.056398868560791, | |
| "min": -20.465923309326172, | |
| "max": 20.013717651367188, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.mean": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.CumulativeReward.sum": { | |
| "value": 0.0, | |
| "min": 0.0, | |
| "max": 0.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.mean": { | |
| "value": -0.11372670623826685, | |
| "min": -0.6428571428571429, | |
| "max": 0.9652000069618225, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Policy.ExtrinsicReward.sum": { | |
| "value": -18.309999704360962, | |
| "min": -54.205000162124634, | |
| "max": 53.77600014209747, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.mean": { | |
| "value": -0.11372670623826685, | |
| "min": -0.6428571428571429, | |
| "max": 0.9652000069618225, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Environment.GroupCumulativeReward.sum": { | |
| "value": -18.309999704360962, | |
| "min": -54.205000162124634, | |
| "max": 53.77600014209747, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 851 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.mean": { | |
| "value": 0.008098788173325981, | |
| "min": 0.005674449715297669, | |
| "max": 0.018914056698607358, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Losses.PolicyLoss.sum": { | |
| "value": 0.008098788173325981, | |
| "min": 0.005674449715297669, | |
| "max": 0.018914056698607358, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.mean": { | |
| "value": 0.09481088022391002, | |
| "min": 0.0011576284072361887, | |
| "max": 0.12343154698610306, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Losses.ValueLoss.sum": { | |
| "value": 0.09481088022391002, | |
| "min": 0.0011576284072361887, | |
| "max": 0.12343154698610306, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.mean": { | |
| "value": 0.0953474298119545, | |
| "min": 0.001153069622038553, | |
| "max": 0.12456244130929311, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Losses.BaselineLoss.sum": { | |
| "value": 0.0953474298119545, | |
| "min": 0.001153069622038553, | |
| "max": 0.12456244130929311, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.mean": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.LearningRate.sum": { | |
| "value": 0.0003, | |
| "min": 0.0003, | |
| "max": 0.0003, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.mean": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.Epsilon.sum": { | |
| "value": 0.20000000000000007, | |
| "min": 0.20000000000000007, | |
| "max": 0.20000000000000007, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.Beta.mean": { | |
| "value": 0.005, | |
| "min": 0.005, | |
| "max": 0.005, | |
| "count": 410 | |
| }, | |
| "SoccerTwos.Policy.Beta.sum": { | |
| "value": 0.005, | |
| "min": 0.005, | |
| "max": 0.005, | |
| "count": 410 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1684305914", | |
| "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", | |
| "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": "1684326360" | |
| }, | |
| "total": 20446.436617105, | |
| "count": 1, | |
| "self": 6.6366969179944135, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.022039218000031724, | |
| "count": 1, | |
| "self": 0.022039218000031724 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 20439.777880969003, | |
| "count": 1, | |
| "self": 17.00123791754595, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 66.82938978198877, | |
| "count": 32, | |
| "self": 66.82938978198877 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 20354.402077808467, | |
| "count": 581427, | |
| "self": 16.553720427978988, | |
| "children": { | |
| "env_step": { | |
| "total": 15114.725241913844, | |
| "count": 581427, | |
| "self": 11886.111546101933, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 3219.7607385578494, | |
| "count": 581427, | |
| "self": 96.34840956989592, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 3123.4123289879535, | |
| "count": 1067736, | |
| "self": 3123.4123289879535 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 8.852957254062403, | |
| "count": 581427, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 20399.3307160576, | |
| "count": 581427, | |
| "is_parallel": true, | |
| "self": 10384.333416753583, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.004083515000047555, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.001060344000279656, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.003023170999767899, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.003023170999767899 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.0368012799999633, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0010314519998928517, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0008096920000753016, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008096920000753016 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.03183866799997759, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.03183866799997759 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0031214680000175576, | |
| "count": 2, | |
| "is_parallel": true, | |
| "self": 0.0006067409999559459, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0025147270000616118, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0025147270000616118 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.07466201700049169, | |
| "count": 62, | |
| "is_parallel": true, | |
| "self": 0.014835434990231988, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0598265820102597, | |
| "count": 248, | |
| "is_parallel": true, | |
| "self": 0.0598265820102597 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 10014.922637287016, | |
| "count": 581426, | |
| "is_parallel": true, | |
| "self": 564.1436291081536, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 364.80537276902044, | |
| "count": 581426, | |
| "is_parallel": true, | |
| "self": 364.80537276902044 | |
| }, | |
| "communicator.exchange": { | |
| "total": 7389.2133546077885, | |
| "count": 581426, | |
| "is_parallel": true, | |
| "self": 7389.2133546077885 | |
| }, | |
| "steps_from_proto": { | |
| "total": 1696.7602808020547, | |
| "count": 1162852, | |
| "is_parallel": true, | |
| "self": 324.84296026705783, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 1371.9173205349969, | |
| "count": 4651408, | |
| "is_parallel": true, | |
| "self": 1371.9173205349969 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 5223.123115466644, | |
| "count": 581427, | |
| "self": 115.56287661098759, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 1900.8606173566482, | |
| "count": 581427, | |
| "self": 1886.9744893836473, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 13.88612797300084, | |
| "count": 18, | |
| "self": 13.88612797300084 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 3206.699621499008, | |
| "count": 410, | |
| "self": 1831.1733181040508, | |
| "children": { | |
| "TorchPOCAOptimizer.update": { | |
| "total": 1375.5263033949573, | |
| "count": 6150, | |
| "self": 1375.5263033949573 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1459997040219605e-06, | |
| "count": 1, | |
| "self": 1.1459997040219605e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 1.5451743150006223, | |
| "count": 1, | |
| "self": 0.717765588000475, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.8274087270001473, | |
| "count": 1, | |
| "self": 0.8274087270001473 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |