{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1745553016662598, "min": 0.7847408652305603, "max": 3.295727014541626, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40916.43359375, "min": 5002.873046875, "max": 154042.765625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 446.8, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 14116.0, "max": 25968.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1216.540961494849, "min": 1194.8258678157067, "max": 1218.1258824734305, "count": 314 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2433.081922989698, "min": 2389.6517356314134, "max": 14392.484805937675, "count": 314 }, "SoccerTwos.Step.mean": { "value": 49999284.0, "min": 9000.0, "max": 49999284.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999284.0, "min": 9000.0, "max": 49999284.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 8.512796193826944e-05, "min": -0.0829419493675232, "max": 0.04899462312459946, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0008512796484865248, "min": -1.244099736213684, "max": 0.48994624614715576, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 8.791960135567933e-05, "min": -0.08300420641899109, "max": 0.04482099786400795, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.0008791959844529629, "min": -1.245063066482544, "max": 0.4482099711894989, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.6666666666666666, "max": 0.3445066690444946, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.0, "max": 5.375599980354309, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.6666666666666666, "max": 0.3445066690444946, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.0, "max": 5.375599980354309, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015997195740540822, "min": 0.010102982061410633, "max": 0.025463151453247217, "count": 2286 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015997195740540822, "min": 0.010102982061410633, "max": 0.025463151453247217, "count": 2286 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 9.7354024332826e-09, "min": 3.8367334078322674e-11, "max": 0.018983715784270317, "count": 2286 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 9.7354024332826e-09, "min": 3.8367334078322674e-11, "max": 0.018983715784270317, "count": 2286 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 9.845815420831776e-09, "min": 3.2968103247377203e-11, "max": 0.01979224164582168, "count": 2286 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 9.845815420831776e-09, "min": 3.2968103247377203e-11, "max": 0.01979224164582168, "count": 2286 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2286 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2286 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2286 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2286 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2286 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2286 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682479286", "python_version": "3.9.16 (main, Apr 26 2023, 09:57:11) \n[GCC 9.4.0]", "command_line_arguments": "/home/isaac/python_envs/py3916_env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "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": "1682533338" }, "total": 54051.992411300016, "count": 1, "self": 0.21920291901915334, "children": { "run_training.setup": { "total": 0.03257302900601644, "count": 1, "self": 0.03257302900601644 }, "TrainerController.start_learning": { "total": 54051.74063535199, "count": 1, "self": 56.852536931459326, "children": { "TrainerController._reset_env": { "total": 17.358610078910715, "count": 249, "self": 17.358610078910715 }, "TrainerController.advance": { "total": 53977.34658055863, "count": 3253376, "self": 55.85743995853409, "children": { "env_step": { "total": 41122.11161842069, "count": 3253376, "self": 30047.647851546877, "children": { "SubprocessEnvManager._take_step": { "total": 11039.89479144357, "count": 3253376, "self": 322.0809364782035, "children": { "TorchPolicy.evaluate": { "total": 10717.813854965367, "count": 6466582, "self": 10717.813854965367 } } }, "workers": { "total": 34.56897543024388, "count": 3253376, "self": 0.0, "children": { "worker_root": { "total": 53962.580403653905, "count": 3253376, "is_parallel": true, "self": 30500.053795634303, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016285839956253767, "count": 2, "is_parallel": true, "self": 0.0003673269966384396, "children": { "_process_rank_one_or_two_observation": { "total": 0.001261256998986937, "count": 8, "is_parallel": true, "self": 0.001261256998986937 } } }, "UnityEnvironment.step": { "total": 0.016129121999256313, "count": 1, "is_parallel": true, "self": 0.00039525399915874004, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006169669941300526, "count": 1, "is_parallel": true, "self": 0.0006169669941300526 }, "communicator.exchange": { "total": 0.013734089996432886, "count": 1, "is_parallel": true, "self": 0.013734089996432886 }, "steps_from_proto": { "total": 0.0013828110095346346, "count": 2, "is_parallel": true, "self": 0.00034920203324873, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010336089762859046, "count": 8, "is_parallel": true, "self": 0.0010336089762859046 } } } } } } }, "UnityEnvironment.step": { "total": 23462.181229369613, "count": 3253375, "is_parallel": true, "self": 1335.4854184746364, "children": { "UnityEnvironment._generate_step_input": { "total": 1116.4319349092402, "count": 3253375, "is_parallel": true, "self": 1116.4319349092402 }, "communicator.exchange": { "total": 16444.75909231197, "count": 3253375, "is_parallel": true, "self": 16444.75909231197 }, "steps_from_proto": { "total": 4565.504783673765, "count": 6506750, "is_parallel": true, "self": 951.9389146392059, "children": { "_process_rank_one_or_two_observation": { "total": 3613.565869034559, "count": 26027000, "is_parallel": true, "self": 3613.565869034559 } } } } }, "steps_from_proto": { "total": 0.34537864998856094, "count": 496, "is_parallel": true, "self": 0.07377804841962643, "children": { "_process_rank_one_or_two_observation": { "total": 0.2716006015689345, "count": 1984, "is_parallel": true, "self": 0.2716006015689345 } } } } } } } } }, "trainer_advance": { "total": 12799.377522179406, "count": 3253376, "self": 413.24750945357664, "children": { "process_trajectory": { "total": 3165.805600452557, "count": 3253376, "self": 3146.166530171584, "children": { "RLTrainer._checkpoint": { "total": 19.6390702809731, "count": 100, "self": 19.6390702809731 } } }, "_update_policy": { "total": 9220.324412273272, "count": 2286, "self": 6459.844267362714, "children": { "TorchPOCAOptimizer.update": { "total": 2760.480144910558, "count": 68580, "self": 2760.480144910558 } } } } } } }, "trainer_threads": { "total": 8.300121407955885e-07, "count": 1, "self": 8.300121407955885e-07 }, "TrainerController._save_models": { "total": 0.18290695297764614, "count": 1, "self": 0.0013288269692566246, "children": { "RLTrainer._checkpoint": { "total": 0.18157812600838952, "count": 1, "self": 0.18157812600838952 } } } } } } }