{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.270434856414795, "min": 3.270434856414795, "max": 3.2957565784454346, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 66245.9296875, "min": 57922.0390625, "max": 105463.984375, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 572.8571428571429, "min": 572.8571428571429, "max": 999.0, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16040.0, "min": 15984.0, "max": 25604.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.6510988651753, "min": 1197.6510988651753, "max": 1200.4622574853702, "count": 4 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9581.208790921402, "min": 2398.517159820343, "max": 14405.547089824442, "count": 4 }, "SoccerTwos.Step.mean": { "value": 49502.0, "min": 9820.0, "max": 49502.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 49502.0, "min": 9820.0, "max": 49502.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03455100208520889, "min": 0.03455100208520889, "max": 0.05008567124605179, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.5528160333633423, "min": 0.415897011756897, "max": 0.7512457370758057, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.035482101142406464, "min": 0.035482101142406464, "max": 0.05012375861406326, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5677136182785034, "min": 0.4534440040588379, "max": 0.7517714500427246, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.25394999980926514, "min": -0.25394999980926514, "max": 0.1096266746520996, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.063199996948242, "min": -4.063199996948242, "max": 1.6444001197814941, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.25394999980926514, "min": -0.25394999980926514, "max": 0.1096266746520996, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.063199996948242, "min": -4.063199996948242, "max": 1.6444001197814941, "count": 5 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017691626998412452, "min": 0.013456214430455778, "max": 0.017691626998412452, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017691626998412452, "min": 0.013456214430455778, "max": 0.017691626998412452, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0015896653446058433, "min": 0.0015896653446058433, "max": 0.001771482858263577, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0015896653446058433, "min": 0.0015896653446058433, "max": 0.001771482858263577, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0016096843791081374, "min": 0.0015241764350018153, "max": 0.0016096843791081374, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0016096843791081374, "min": 0.0015241764350018153, "max": 0.0016096843791081374, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.2, "min": 0.2, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.2, "min": 0.2, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678764456", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Notes\\drl-course\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos_light --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678764807" }, "total": 351.0104281, "count": 1, "self": 2.9374502000000575, "children": { "run_training.setup": { "total": 0.23172039999999994, "count": 1, "self": 0.23172039999999994 }, "TrainerController.start_learning": { "total": 347.8412575, "count": 1, "self": 0.15428849999875638, "children": { "TrainerController._reset_env": { "total": 19.2141545, "count": 1, "self": 19.2141545 }, "TrainerController.advance": { "total": 328.13108200000124, "count": 3656, "self": 0.17994720000052666, "children": { "env_step": { "total": 145.71569330000034, "count": 3656, "self": 114.14501089999965, "children": { "SubprocessEnvManager._take_step": { "total": 31.455057800000354, "count": 3656, "self": 1.0930717999998052, "children": { "TorchPolicy.evaluate": { "total": 30.36198600000055, "count": 7266, "self": 30.36198600000055 } } }, "workers": { "total": 0.11562460000034491, "count": 3656, "self": 0.0, "children": { "worker_root": { "total": 327.1890946000002, "count": 3656, "is_parallel": true, "self": 235.7860736000015, "children": { "steps_from_proto": { "total": 0.011300399999999655, "count": 2, "is_parallel": true, "self": 0.003762999999995742, "children": { "_process_rank_one_or_two_observation": { "total": 0.007537400000003913, "count": 8, "is_parallel": true, "self": 0.007537400000003913 } } }, "UnityEnvironment.step": { "total": 91.3917205999987, "count": 3656, "is_parallel": true, "self": 5.103755799999291, "children": { "UnityEnvironment._generate_step_input": { "total": 4.572379299999508, "count": 3656, "is_parallel": true, "self": 4.572379299999508 }, "communicator.exchange": { "total": 64.59551070000042, "count": 3656, "is_parallel": true, "self": 64.59551070000042 }, "steps_from_proto": { "total": 17.120074799999486, "count": 7312, "is_parallel": true, "self": 3.413218499997466, "children": { "_process_rank_one_or_two_observation": { "total": 13.70685630000202, "count": 29248, "is_parallel": true, "self": 13.70685630000202 } } } } } } } } } } }, "trainer_advance": { "total": 182.23544150000038, "count": 3656, "self": 0.8856490000020472, "children": { "process_trajectory": { "total": 27.986286299998337, "count": 3656, "self": 27.986286299998337 }, "_update_policy": { "total": 153.3635062, "count": 2, "self": 11.564430700000145, "children": { "TorchPOCAOptimizer.update": { "total": 141.79907549999984, "count": 63, "self": 141.79907549999984 } } } } } } }, "trainer_threads": { "total": 6.199999972977821e-06, "count": 1, "self": 6.199999972977821e-06 }, "TrainerController._save_models": { "total": 0.3417263000000048, "count": 1, "self": 0.012669200000004821, "children": { "RLTrainer._checkpoint": { "total": 0.3290571, "count": 1, "self": 0.3290571 } } } } } } }