{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4788085222244263, "min": 1.34537935256958, "max": 3.2956905364990234, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 25127.9140625, "min": 16445.171875, "max": 145786.125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.44155844155844, "min": 39.942622950819676, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19848.0, "min": 7992.0, "max": 28332.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1895.7613020306055, "min": 1201.592804267964, "max": 1920.2364514241071, "count": 4546 }, "SoccerTwos.Self-play.ELO.sum": { "value": 291947.24051271327, "min": 2403.84684830682, "max": 416879.5351197595, "count": 4546 }, "SoccerTwos.Step.mean": { "value": 49999916.0, "min": 9184.0, "max": 49999916.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999916.0, "min": 9184.0, "max": 49999916.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.045010194182395935, "min": -0.15087659657001495, "max": 0.1586652249097824, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.88655948638916, "min": -28.36479949951172, "max": 23.482452392578125, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04811400547623634, "min": -0.15700209140777588, "max": 0.15648241341114044, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.361443042755127, "min": -29.516393661499023, "max": 23.17345428466797, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.20982221996082978, "min": -0.7889999991113489, "max": 0.4695555501514011, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 32.10279965400696, "min": -60.55800008773804, "max": 59.11360025405884, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.20982221996082978, "min": -0.7889999991113489, "max": 0.4695555501514011, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 32.10279965400696, "min": -60.55800008773804, "max": 59.11360025405884, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018770876314859682, "min": 0.010020536121252614, "max": 0.026517125661484897, "count": 2405 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018770876314859682, "min": 0.010020536121252614, "max": 0.026517125661484897, "count": 2405 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09144515817364057, "min": 3.3547097721964294e-08, "max": 0.131473595649004, "count": 2405 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09144515817364057, "min": 3.3547097721964294e-08, "max": 0.131473595649004, "count": 2405 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09309406379858652, "min": 4.3677706192587116e-08, "max": 0.135417403280735, "count": 2405 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09309406379858652, "min": 4.3677706192587116e-08, "max": 0.135417403280735, "count": 2405 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2405 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2405 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2405 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2405 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2405 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2405 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675620254", "python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]", "command_line_arguments": "/home/yucjin/hugging_face_rl/unit7/venv/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": "1675708861" }, "total": 88607.92426025501, "count": 1, "self": 0.21856925400788896, "children": { "run_training.setup": { "total": 0.008596899999247398, "count": 1, "self": 0.008596899999247398 }, "TrainerController.start_learning": { "total": 88607.69709410101, "count": 1, "self": 54.33353889726277, "children": { "TrainerController._reset_env": { "total": 7.953261757964356, "count": 250, "self": 7.953261757964356 }, "TrainerController.advance": { "total": 88545.25049504777, "count": 3420118, "self": 50.14558512021904, "children": { "env_step": { "total": 67936.5814669147, "count": 3420118, "self": 43416.33377479577, "children": { "SubprocessEnvManager._take_step": { "total": 24488.584984037847, "count": 3420118, "self": 288.33730446321715, "children": { "TorchPolicy.evaluate": { "total": 24200.24767957463, "count": 6313434, "self": 24200.24767957463 } } }, "workers": { "total": 31.662708081072196, "count": 3420118, "self": 0.0, "children": { "worker_root": { "total": 88484.73229627071, "count": 3420118, "is_parallel": true, "self": 50667.68108681378, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001849100004619686, "count": 2, "is_parallel": true, "self": 0.0005407000026025344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013084000020171516, "count": 8, "is_parallel": true, "self": 0.0013084000020171516 } } }, "UnityEnvironment.step": { "total": 0.028766398998413933, "count": 1, "is_parallel": true, "self": 0.00045390000013867393, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003077000001212582, "count": 1, "is_parallel": true, "self": 0.0003077000001212582 }, "communicator.exchange": { "total": 0.02654359900043346, "count": 1, "is_parallel": true, "self": 0.02654359900043346 }, "steps_from_proto": { "total": 0.0014611999977205414, "count": 2, "is_parallel": true, "self": 0.00028139999994891696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011797999977716245, "count": 8, "is_parallel": true, "self": 0.0011797999977716245 } } } } } } }, "UnityEnvironment.step": { "total": 37816.752694438124, "count": 3420117, "is_parallel": true, "self": 1171.1702581627032, "children": { "UnityEnvironment._generate_step_input": { "total": 846.923472165432, "count": 3420117, "is_parallel": true, "self": 846.923472165432 }, "communicator.exchange": { "total": 31938.347590114598, "count": 3420117, "is_parallel": true, "self": 31938.347590114598 }, "steps_from_proto": { "total": 3860.311373995395, "count": 6840234, "is_parallel": true, "self": 810.0337141514356, "children": { "_process_rank_one_or_two_observation": { "total": 3050.2776598439596, "count": 27360936, "is_parallel": true, "self": 3050.2776598439596 } } } } }, "steps_from_proto": { "total": 0.29851501880330034, "count": 498, "is_parallel": true, "self": 0.06205058093837579, "children": { "_process_rank_one_or_two_observation": { "total": 0.23646443786492455, "count": 1992, "is_parallel": true, "self": 0.23646443786492455 } } } } } } } } }, "trainer_advance": { "total": 20558.52344301286, "count": 3420118, "self": 353.95522478349085, "children": { "process_trajectory": { "total": 10449.847205032387, "count": 3420118, "self": 10427.388773734434, "children": { "RLTrainer._checkpoint": { "total": 22.45843129795321, "count": 100, "self": 22.45843129795321 } } }, "_update_policy": { "total": 9754.72101319698, "count": 2405, "self": 4998.611239978134, "children": { "TorchPOCAOptimizer.update": { "total": 4756.109773218846, "count": 72159, "self": 4756.109773218846 } } } } } } }, "trainer_threads": { "total": 5.00003807246685e-07, "count": 1, "self": 5.00003807246685e-07 }, "TrainerController._save_models": { "total": 0.15979789799894206, "count": 1, "self": 0.0011017839860869572, "children": { "RLTrainer._checkpoint": { "total": 0.1586961140128551, "count": 1, "self": 0.1586961140128551 } } } } } } }