{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.276836395263672, "min": 3.276836395263672, "max": 3.295710563659668, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 99301.25, "min": 49026.21875, "max": 116492.6796875, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 494.1, "min": 402.53846153846155, "max": 826.5, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19764.0, "min": 13904.0, "max": 26448.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.973240627599, "min": 1196.1575554143353, "max": 1200.0057398668362, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9575.785925020791, "min": 4784.630221657341, "max": 14400.068878402035, "count": 5 }, "SoccerTwos.Step.mean": { "value": 49481.0, "min": 9240.0, "max": 49481.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 49481.0, "min": 9240.0, "max": 49481.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.017755256965756416, "min": 0.015964774414896965, "max": 0.017755256965756416, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.35510513186454773, "min": 0.19157728552818298, "max": 0.4559280276298523, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02090129442512989, "min": 0.01710919477045536, "max": 0.021780377253890038, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.4180258810520172, "min": 0.20531034469604492, "max": 0.5434314608573914, "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": -0.09177999794483185, "min": -0.183007694207705, "max": -0.025988236946218154, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.835599958896637, "min": -4.75820004940033, "max": -0.4418000280857086, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09177999794483185, "min": -0.183007694207705, "max": -0.025988236946218154, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.835599958896637, "min": -4.75820004940033, "max": -0.4418000280857086, "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": 0.020048053671295443, "min": 0.013956675225441965, "max": 0.020048053671295443, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.020048053671295443, "min": 0.013956675225441965, "max": 0.020048053671295443, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003968271519988775, "min": 0.003968271519988775, "max": 0.004949383491960665, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003968271519988775, "min": 0.003968271519988775, "max": 0.004949383491960665, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.004005392733961344, "min": 0.004005392733961344, "max": 0.004720366552161673, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.004005392733961344, "min": 0.004005392733961344, "max": 0.004720366552161673, "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": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701133238", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\nicos\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701133626" }, "total": 387.8955280000009, "count": 1, "self": 0.7812288999994053, "children": { "run_training.setup": { "total": 0.31763080000382615, "count": 1, "self": 0.31763080000382615 }, "TrainerController.start_learning": { "total": 386.7966682999977, "count": 1, "self": 0.27002319980965694, "children": { "TrainerController._reset_env": { "total": 11.539739800005918, "count": 3, "self": 11.539739800005918 }, "TrainerController.advance": { "total": 374.41705950017786, "count": 4322, "self": 0.310172600155056, "children": { "env_step": { "total": 238.48301200011338, "count": 4322, "self": 186.4302416002538, "children": { "SubprocessEnvManager._take_step": { "total": 51.87918779975735, "count": 4322, "self": 2.039363099473121, "children": { "TorchPolicy.evaluate": { "total": 49.839824700284225, "count": 8600, "self": 49.839824700284225 } } }, "workers": { "total": 0.17358260010223603, "count": 4322, "self": 0.0, "children": { "worker_root": { "total": 374.8027044998162, "count": 4322, "is_parallel": true, "self": 226.2311640998887, "children": { "steps_from_proto": { "total": 0.016620599992165808, "count": 6, "is_parallel": true, "self": 0.0030250999989220873, "children": { "_process_rank_one_or_two_observation": { "total": 0.01359549999324372, "count": 24, "is_parallel": true, "self": 0.01359549999324372 } } }, "UnityEnvironment.step": { "total": 148.5549197999353, "count": 4322, "is_parallel": true, "self": 8.05323410051642, "children": { "UnityEnvironment._generate_step_input": { "total": 6.7022263000835665, "count": 4322, "is_parallel": true, "self": 6.7022263000835665 }, "communicator.exchange": { "total": 106.79594819962222, "count": 4322, "is_parallel": true, "self": 106.79594819962222 }, "steps_from_proto": { "total": 27.003511199713103, "count": 8644, "is_parallel": true, "self": 5.400286799726018, "children": { "_process_rank_one_or_two_observation": { "total": 21.603224399987084, "count": 34576, "is_parallel": true, "self": 21.603224399987084 } } } } } } } } } } }, "trainer_advance": { "total": 135.62387489990942, "count": 4322, "self": 1.2072394003043883, "children": { "process_trajectory": { "total": 24.746448899597453, "count": 4322, "self": 24.746448899597453 }, "_update_policy": { "total": 109.67018660000758, "count": 2, "self": 14.201118899989524, "children": { "TorchPOCAOptimizer.update": { "total": 95.46906770001806, "count": 60, "self": 95.46906770001806 } } } } } } }, "trainer_threads": { "total": 3.4000040614046156e-06, "count": 1, "self": 3.4000040614046156e-06 }, "TrainerController._save_models": { "total": 0.5698424000001978, "count": 1, "self": 0.022616599999309983, "children": { "RLTrainer._checkpoint": { "total": 0.5472258000008878, "count": 1, "self": 0.5472258000008878 } } } } } } }