{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8687857389450073, "min": 0.8687857389450073, "max": 2.6227786540985107, "count": 18 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8304.72265625, "min": 8304.72265625, "max": 24682.32421875, "count": 18 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 29984.0, "max": 199960.0, "count": 18 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 29984.0, "max": 199960.0, "count": 18 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.608823776245117, "min": 2.579326868057251, "max": 12.608823776245117, "count": 18 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.720703125, "min": 172.8148956298828, "max": 2535.80615234375, "count": 18 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 18 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 2189.0, "max": 10945.0, "count": 18 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06342106889682256, "min": 0.06342106889682256, "max": 0.07515152978286256, "count": 18 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25368427558729023, "min": 0.07160567258627755, "max": 0.3757576489143128, "count": 18 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20883192932781053, "min": 0.19779164382055697, "max": 0.2749632154025283, "count": 18 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8353277173112421, "min": 0.2718317747736971, "max": 1.3748160770126416, "count": 18 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.00025736401421199996, "count": 18 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.00123732008756, "count": 18 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.18578800000000004, "count": 18 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.18578800000000004, "max": 0.9124400000000001, "count": 18 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.0042908212, "count": 18 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.020630756, "count": 18 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 7.909090909090909, "max": 25.454545454545453, "count": 18 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 87.0, "max": 1359.0, "count": 18 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 7.909090909090909, "max": 25.454545454545453, "count": 18 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 87.0, "max": 1359.0, "count": 18 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 18 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 18 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692816669", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "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": "1692817078" }, "total": 409.725161716, "count": 1, "self": 0.4358088129997668, "children": { "run_training.setup": { "total": 0.03939240900012919, "count": 1, "self": 0.03939240900012919 }, "TrainerController.start_learning": { "total": 409.2499604940001, "count": 1, "self": 0.48618473099691073, "children": { "TrainerController._reset_env": { "total": 5.233312679999926, "count": 1, "self": 5.233312679999926 }, "TrainerController.advance": { "total": 403.3927433660033, "count": 15803, "self": 0.22470167300343746, "children": { "env_step": { "total": 403.16804169299985, "count": 15803, "self": 291.23483566800815, "children": { "SubprocessEnvManager._take_step": { "total": 111.69486024400476, "count": 15803, "self": 1.4851255690232392, "children": { "TorchPolicy.evaluate": { "total": 110.20973467498152, "count": 15803, "self": 110.20973467498152 } } }, "workers": { "total": 0.23834578098694692, "count": 15803, "self": 0.0, "children": { "worker_root": { "total": 407.9182839439993, "count": 15803, "is_parallel": true, "self": 193.33293445200252, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027271930000551947, "count": 1, "is_parallel": true, "self": 0.0006626520000736491, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020645409999815456, "count": 10, "is_parallel": true, "self": 0.0020645409999815456 } } }, "UnityEnvironment.step": { "total": 0.08112083999981223, "count": 1, "is_parallel": true, "self": 0.0006179699998938304, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041931200007638836, "count": 1, "is_parallel": true, "self": 0.00041931200007638836 }, "communicator.exchange": { "total": 0.07792154999992817, "count": 1, "is_parallel": true, "self": 0.07792154999992817 }, "steps_from_proto": { "total": 0.0021620079999138397, "count": 1, "is_parallel": true, "self": 0.0005079440002191404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016540639996946993, "count": 10, "is_parallel": true, "self": 0.0016540639996946993 } } } } } } }, "UnityEnvironment.step": { "total": 214.5853494919968, "count": 15802, "is_parallel": true, "self": 8.957819087994494, "children": { "UnityEnvironment._generate_step_input": { "total": 4.497118653010602, "count": 15802, "is_parallel": true, "self": 4.497118653010602 }, "communicator.exchange": { "total": 169.9384629499839, "count": 15802, "is_parallel": true, "self": 169.9384629499839 }, "steps_from_proto": { "total": 31.19194880100781, "count": 15802, "is_parallel": true, "self": 5.786408259057453, "children": { "_process_rank_one_or_two_observation": { "total": 25.40554054195036, "count": 158020, "is_parallel": true, "self": 25.40554054195036 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001401260001330229, "count": 1, "self": 0.0001401260001330229, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 399.85658967214727, "count": 393732, "is_parallel": true, "self": 9.073231241175108, "children": { "process_trajectory": { "total": 221.7125994919727, "count": 393732, "is_parallel": true, "self": 220.46351121297266, "children": { "RLTrainer._checkpoint": { "total": 1.2490882790000342, "count": 4, "is_parallel": true, "self": 1.2490882790000342 } } }, "_update_policy": { "total": 169.07075893899946, "count": 78, "is_parallel": true, "self": 61.56930568899725, "children": { "TorchPPOOptimizer.update": { "total": 107.50145325000221, "count": 3975, "is_parallel": true, "self": 107.50145325000221 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13757959099984873, "count": 1, "self": 0.001011767999671065, "children": { "RLTrainer._checkpoint": { "total": 0.13656782300017767, "count": 1, "self": 0.13656782300017767 } } } } } } }