{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1900360584259033, "min": 2.167386770248413, "max": 3.295736312866211, "count": 555 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43940.8828125, "min": 13246.4296875, "max": 132291.734375, "count": 555 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.00917431192661, "min": 42.87719298245614, "max": 999.0, "count": 555 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 16332.0, "max": 23820.0, "count": 555 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1464.9027600655795, "min": 1194.729362064036, "max": 1485.5992744352004, "count": 486 }, "SoccerTwos.Self-play.ELO.sum": { "value": 319348.80169429636, "min": 2390.182201560855, "max": 335153.05253767193, "count": 486 }, "SoccerTwos.Step.mean": { "value": 5549971.0, "min": 9764.0, "max": 5549971.0, "count": 555 }, "SoccerTwos.Step.sum": { "value": 5549971.0, "min": 9764.0, "max": 5549971.0, "count": 555 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06239335611462593, "min": -0.0794447511434555, "max": 0.1867370456457138, "count": 555 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -13.601751327514648, "min": -13.601751327514648, "max": 29.504453659057617, "count": 555 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06617218255996704, "min": -0.07153940945863724, "max": 0.18480005860328674, "count": 555 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -14.425535202026367, "min": -14.425535202026367, "max": 29.198408126831055, "count": 555 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 555 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 555 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09514495292934802, "min": -0.5714285714285714, "max": 0.4863862107539999, "count": 555 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.74159973859787, "min": -45.99880003929138, "max": 63.66600012779236, "count": 555 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09514495292934802, "min": -0.5714285714285714, "max": 0.4863862107539999, "count": 555 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.74159973859787, "min": -45.99880003929138, "max": 63.66600012779236, "count": 555 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 555 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 555 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01725150128477253, "min": 0.01080811139739429, "max": 0.023342306698517255, "count": 262 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01725150128477253, "min": 0.01080811139739429, "max": 0.023342306698517255, "count": 262 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10361563538511594, "min": 1.3276717178693312e-05, "max": 0.10361563538511594, "count": 262 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10361563538511594, "min": 1.3276717178693312e-05, "max": 0.10361563538511594, "count": 262 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10657977908849717, "min": 1.3994739432140097e-05, "max": 0.10657977908849717, "count": 262 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10657977908849717, "min": 1.3994739432140097e-05, "max": 0.10657977908849717, "count": 262 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 262 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 262 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 262 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 262 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 262 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 262 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675705169", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/allen/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos2 --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": "1675712464" }, "total": 7294.743106747001, "count": 1, "self": 0.0038835930008644937, "children": { "run_training.setup": { "total": 0.010265704999710579, "count": 1, "self": 0.010265704999710579 }, "TrainerController.start_learning": { "total": 7294.728957449, "count": 1, "self": 6.639359528008754, "children": { "TrainerController._reset_env": { "total": 3.570394211999428, "count": 28, "self": 3.570394211999428 }, "TrainerController.advance": { "total": 7284.133262107991, "count": 367564, "self": 6.37577275298645, "children": { "env_step": { "total": 5088.976443028898, "count": 367564, "self": 3845.1727736048297, "children": { "SubprocessEnvManager._take_step": { "total": 1239.6260531680828, "count": 367564, "self": 35.141112057127884, "children": { "TorchPolicy.evaluate": { "total": 1204.4849411109549, "count": 710623, "self": 1204.4849411109549 } } }, "workers": { "total": 4.177616255985413, "count": 367563, "self": 0.0, "children": { "worker_root": { "total": 7285.334805494049, "count": 367563, "is_parallel": true, "self": 4170.375242454926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001846062000367965, "count": 2, "is_parallel": true, "self": 0.0004559230001177639, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013901390002502012, "count": 8, "is_parallel": true, "self": 0.0013901390002502012 } } }, "UnityEnvironment.step": { "total": 0.019023241000013513, "count": 1, "is_parallel": true, "self": 0.00046379700006582425, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003501430001051631, "count": 1, "is_parallel": true, "self": 0.0003501430001051631 }, "communicator.exchange": { "total": 0.01681665800015253, "count": 1, "is_parallel": true, "self": 0.01681665800015253 }, "steps_from_proto": { "total": 0.001392642999689997, "count": 2, "is_parallel": true, "self": 0.0002951200003735721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010975229993164248, "count": 8, "is_parallel": true, "self": 0.0010975229993164248 } } } } } } }, "UnityEnvironment.step": { "total": 3114.921974966126, "count": 367562, "is_parallel": true, "self": 171.03351007269248, "children": { "UnityEnvironment._generate_step_input": { "total": 114.09493637799596, "count": 367562, "is_parallel": true, "self": 114.09493637799596 }, "communicator.exchange": { "total": 2321.451533335002, "count": 367562, "is_parallel": true, "self": 2321.451533335002 }, "steps_from_proto": { "total": 508.3419951804358, "count": 735124, "is_parallel": true, "self": 104.44729754152013, "children": { "_process_rank_one_or_two_observation": { "total": 403.89469763891566, "count": 2940496, "is_parallel": true, "self": 403.89469763891566 } } } } }, "steps_from_proto": { "total": 0.03758807299709588, "count": 54, "is_parallel": true, "self": 0.007700384010149719, "children": { "_process_rank_one_or_two_observation": { "total": 0.02988768898694616, "count": 216, "is_parallel": true, "self": 0.02988768898694616 } } } } } } } } }, "trainer_advance": { "total": 2188.7810463261067, "count": 367563, "self": 47.6774538809982, "children": { "process_trajectory": { "total": 495.26592037411456, "count": 367563, "self": 491.52929729811376, "children": { "RLTrainer._checkpoint": { "total": 3.7366230760007966, "count": 11, "self": 3.7366230760007966 } } }, "_update_policy": { "total": 1645.837672070994, "count": 262, "self": 671.8193251020589, "children": { "TorchPOCAOptimizer.update": { "total": 974.018346968935, "count": 7860, "self": 974.018346968935 } } } } } } }, "trainer_threads": { "total": 9.809991752263159e-07, "count": 1, "self": 9.809991752263159e-07 }, "TrainerController._save_models": { "total": 0.38594062000083795, "count": 1, "self": 0.0010728730012488086, "children": { "RLTrainer._checkpoint": { "total": 0.38486774699958914, "count": 1, "self": 0.38486774699958914 } } } } } } }