{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.280968427658081, "min": 3.280968427658081, "max": 3.295750379562378, "count": 3 }, "SoccerTwos.Policy.Entropy.sum": { "value": 22363.080078125, "min": 22363.080078125, "max": 105464.015625, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 933.4, "min": 720.5555555555555, "max": 999.0, "count": 3 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18668.0, "min": 15984.0, "max": 25940.0, "count": 3 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1197.29039462519, "min": 1197.29039462519, "max": 1198.9330538896995, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2394.58078925038, "min": 2394.58078925038, "max": 14387.196646676395, "count": 2 }, "SoccerTwos.Step.mean": { "value": 29660.0, "min": 9988.0, "max": 29660.0, "count": 3 }, "SoccerTwos.Step.sum": { "value": 29660.0, "min": 9988.0, "max": 29660.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09966204315423965, "min": -0.09966204315423965, "max": -0.09445656090974808, "count": 3 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.9966204166412354, "min": -1.4168685674667358, "max": -0.9445655941963196, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08919508755207062, "min": -0.09446826577186584, "max": -0.08919508755207062, "count": 3 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8919509053230286, "min": -1.4169690608978271, "max": -0.8919509053230286, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1, "min": -0.4471733351548513, "max": 0.0, "count": 3 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.0, "min": -6.707600027322769, "max": 0.0, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1, "min": -0.4471733351548513, "max": 0.0, "count": 3 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.0, "min": -6.707600027322769, "max": 0.0, "count": 3 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01017338082116718, "min": 0.01017338082116718, "max": 0.01017338082116718, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01017338082116718, "min": 0.01017338082116718, "max": 0.01017338082116718, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003858987311832607, "min": 0.003858987311832607, "max": 0.003858987311832607, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003858987311832607, "min": 0.003858987311832607, "max": 0.003858987311832607, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003363465463432173, "min": 0.003363465463432173, "max": 0.003363465463432173, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003363465463432173, "min": 0.003363465463432173, "max": 0.003363465463432173, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719161303", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./SoccerTwos.yaml --env=./SoccerTwos.x86_64 --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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719161448" }, "total": 145.59893467400002, "count": 1, "self": 0.16580648800004383, "children": { "run_training.setup": { "total": 0.06913131400006023, "count": 1, "self": 0.06913131400006023 }, "TrainerController.start_learning": { "total": 145.36399687199992, "count": 1, "self": 0.07660826500523399, "children": { "TrainerController._reset_env": { "total": 3.5830633079999643, "count": 1, "self": 3.5830633079999643 }, "TrainerController.advance": { "total": 141.26078202899453, "count": 2059, "self": 0.08111156999098057, "children": { "env_step": { "total": 68.62431423400722, "count": 2059, "self": 55.63074833300584, "children": { "SubprocessEnvManager._take_step": { "total": 12.951577098997632, "count": 2059, "self": 0.4328248299966617, "children": { "TorchPolicy.evaluate": { "total": 12.51875226900097, "count": 4100, "self": 12.51875226900097 } } }, "workers": { "total": 0.04198880200374333, "count": 2058, "self": 0.0, "children": { "worker_root": { "total": 144.71544515900496, "count": 2058, "is_parallel": true, "self": 98.58745785700762, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010739521000232344, "count": 2, "is_parallel": true, "self": 0.004641954000589976, "children": { "_process_rank_one_or_two_observation": { "total": 0.006097566999642368, "count": 8, "is_parallel": true, "self": 0.006097566999642368 } } }, "UnityEnvironment.step": { "total": 0.04766169300000911, "count": 1, "is_parallel": true, "self": 0.0014958370002204902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009980229999655421, "count": 1, "is_parallel": true, "self": 0.0009980229999655421 }, "communicator.exchange": { "total": 0.040985858999874836, "count": 1, "is_parallel": true, "self": 0.040985858999874836 }, "steps_from_proto": { "total": 0.004181973999948241, "count": 2, "is_parallel": true, "self": 0.0007969130001583835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033850609997898573, "count": 8, "is_parallel": true, "self": 0.0033850609997898573 } } } } } } }, "UnityEnvironment.step": { "total": 46.12798730199734, "count": 2057, "is_parallel": true, "self": 2.8436289059961837, "children": { "UnityEnvironment._generate_step_input": { "total": 2.011639425005569, "count": 2057, "is_parallel": true, "self": 2.011639425005569 }, "communicator.exchange": { "total": 32.42867483099917, "count": 2057, "is_parallel": true, "self": 32.42867483099917 }, "steps_from_proto": { "total": 8.844044139996413, "count": 4114, "is_parallel": true, "self": 1.5101265559958392, "children": { "_process_rank_one_or_two_observation": { "total": 7.333917584000574, "count": 16456, "is_parallel": true, "self": 7.333917584000574 } } } } } } } } } } }, "trainer_advance": { "total": 72.55535622499633, "count": 2058, "self": 0.44111298998973325, "children": { "process_trajectory": { "total": 12.692461847006598, "count": 2058, "self": 12.692461847006598 }, "_update_policy": { "total": 59.421781388, "count": 1, "self": 4.662049969999998, "children": { "TorchPOCAOptimizer.update": { "total": 54.759731418, "count": 30, "self": 54.759731418 } } } } } } }, "trainer_threads": { "total": 1.6290000530716497e-06, "count": 1, "self": 1.6290000530716497e-06 }, "TrainerController._save_models": { "total": 0.44354164100013804, "count": 1, "self": 0.004579418000048463, "children": { "RLTrainer._checkpoint": { "total": 0.4389622230000896, "count": 1, "self": 0.4389622230000896 } } } } } } }