{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.899707317352295, "min": 1.8666845560073853, "max": 2.2551064491271973, "count": 206 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36231.21875, "min": 14427.431640625, "max": 48437.265625, "count": 206 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.109756097560975, "min": 43.75229357798165, "max": 80.62295081967213, "count": 206 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19716.0, "min": 5484.0, "max": 20484.0, "count": 206 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1270.6737923228902, "min": 1262.5812209069436, "max": 1304.2159453733468, "count": 206 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208390.501940954, "min": 60869.15219965749, "max": 275722.76527779544, "count": 206 }, "SoccerTwos.Step.mean": { "value": 10649974.0, "min": 8599961.0, "max": 10649974.0, "count": 206 }, "SoccerTwos.Step.sum": { "value": 10649974.0, "min": 8599961.0, "max": 10649974.0, "count": 206 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.012548467144370079, "min": -0.14724032580852509, "max": 0.07918369770050049, "count": 206 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.057948589324951, "min": -23.85293197631836, "max": 13.698780059814453, "count": 206 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010434726253151894, "min": -0.14370520412921906, "max": 0.08216734975576401, "count": 206 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.7112951278686523, "min": -23.280242919921875, "max": 14.214951515197754, "count": 206 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 206 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 206 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.17152195151259259, "min": -0.2927771418435233, "max": 0.30314271324243974, "count": 206 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -28.129600048065186, "min": -51.97079956531525, "max": 60.325399935245514, "count": 206 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.17152195151259259, "min": -0.2927771418435233, "max": 0.30314271324243974, "count": 206 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -28.129600048065186, "min": -51.97079956531525, "max": 60.325399935245514, "count": 206 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 206 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 206 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017357751993646767, "min": 0.011962342753152673, "max": 0.023411121196113528, "count": 99 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017357751993646767, "min": 0.011962342753152673, "max": 0.023411121196113528, "count": 99 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11244878272215525, "min": 0.08854094247023264, "max": 0.11486384173234304, "count": 99 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11244878272215525, "min": 0.08854094247023264, "max": 0.11486384173234304, "count": 99 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11469231645266215, "min": 0.08988887096444766, "max": 0.11737564106782278, "count": 99 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11469231645266215, "min": 0.08988887096444766, "max": 0.11737564106782278, "count": 99 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 99 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 99 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 99 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 99 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 99 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 99 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697582174", "python_version": "3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]", "command_line_arguments": "/home/foreverip/miniconda3/envs/huggingface-rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1697588133" }, "total": 5958.1983035700005, "count": 1, "self": 0.00577861400142865, "children": { "run_training.setup": { "total": 0.06641858099919773, "count": 1, "self": 0.06641858099919773 }, "TrainerController.start_learning": { "total": 5958.126106375, "count": 1, "self": 3.9599314957204115, "children": { "TrainerController._reset_env": { "total": 7.414259091000531, "count": 12, "self": 7.414259091000531 }, "TrainerController.advance": { "total": 5946.400784525277, "count": 143194, "self": 4.034141674756938, "children": { "env_step": { "total": 3913.242215924148, "count": 143194, "self": 3009.8085575492078, "children": { "SubprocessEnvManager._take_step": { "total": 900.8909132520566, "count": 143194, "self": 23.254369332249553, "children": { "TorchPolicy.evaluate": { "total": 877.6365439198071, "count": 258306, "self": 877.6365439198071 } } }, "workers": { "total": 2.542745122883389, "count": 143194, "self": 0.0, "children": { "worker_root": { "total": 5942.4556625693085, "count": 143194, "is_parallel": true, "self": 3374.4597361534816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002415871999801311, "count": 2, "is_parallel": true, "self": 0.0005861650015503983, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018297069982509129, "count": 8, "is_parallel": true, "self": 0.0018297069982509129 } } }, "UnityEnvironment.step": { "total": 0.024754271000347217, "count": 1, "is_parallel": true, "self": 0.0005256350013951305, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004785609999089502, "count": 1, "is_parallel": true, "self": 0.0004785609999089502 }, "communicator.exchange": { "total": 0.02202964299976884, "count": 1, "is_parallel": true, "self": 0.02202964299976884 }, "steps_from_proto": { "total": 0.0017204319992742967, "count": 2, "is_parallel": true, "self": 0.0004128049995415495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013076269997327472, "count": 8, "is_parallel": true, "self": 0.0013076269997327472 } } } } } } }, "steps_from_proto": { "total": 0.02348342799996317, "count": 22, "is_parallel": true, "self": 0.004550374004793412, "children": { "_process_rank_one_or_two_observation": { "total": 0.018933053995169757, "count": 88, "is_parallel": true, "self": 0.018933053995169757 } } }, "UnityEnvironment.step": { "total": 2567.972442987827, "count": 143193, "is_parallel": true, "self": 125.09512984815319, "children": { "UnityEnvironment._generate_step_input": { "total": 70.23697277520569, "count": 143193, "is_parallel": true, "self": 70.23697277520569 }, "communicator.exchange": { "total": 2033.0428889390814, "count": 143193, "is_parallel": true, "self": 2033.0428889390814 }, "steps_from_proto": { "total": 339.5974514253867, "count": 286386, "is_parallel": true, "self": 62.99657596209545, "children": { "_process_rank_one_or_two_observation": { "total": 276.60087546329123, "count": 1145544, "is_parallel": true, "self": 276.60087546329123 } } } } } } } } } } }, "trainer_advance": { "total": 2029.1244269263725, "count": 143194, "self": 27.13517088637036, "children": { "process_trajectory": { "total": 564.4148560900085, "count": 143194, "self": 562.889965740007, "children": { "RLTrainer._checkpoint": { "total": 1.5248903500014421, "count": 4, "self": 1.5248903500014421 } } }, "_update_policy": { "total": 1437.5743999499937, "count": 100, "self": 333.9592402840408, "children": { "TorchPOCAOptimizer.update": { "total": 1103.615159665953, "count": 2986, "self": 1103.615159665953 } } } } } } }, "trainer_threads": { "total": 1.3370008673518896e-06, "count": 1, "self": 1.3370008673518896e-06 }, "TrainerController._save_models": { "total": 0.3511299260007945, "count": 1, "self": 0.0020111730009375606, "children": { "RLTrainer._checkpoint": { "total": 0.34911875299985695, "count": 1, "self": 0.34911875299985695 } } } } } } }