{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0800565481185913, "min": 1.0800565481185913, "max": 2.865978240966797, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10300.4990234375, "min": 10300.4990234375, "max": 27921.345703125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.852461814880371, "min": 0.7957610487937927, "max": 12.852461814880371, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.22998046875, "min": 75.59729766845703, "max": 2573.947509765625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 4378.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.065277744479353, "min": 0.060407346636387874, "max": 0.07510465324009477, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.261110977917412, "min": 0.14982889127899326, "max": 0.36340564895791055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2090834575686969, "min": 0.17593101335360722, "max": 0.3001500289229786, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8363338302747876, "min": 0.35186202670721445, "max": 1.4312542606802547, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.0260976579999984e-06, "min": 7.0260976579999984e-06, "max": 0.000287526004158, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.8104390631999994e-05, "min": 2.8104390631999994e-05, "max": 0.0013138800620399998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10234199999999999, "min": 0.10234199999999999, "max": 0.19584200000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40936799999999995, "min": 0.39168400000000003, "max": 0.93796, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001268658, "min": 0.0001268658, "max": 0.004792515800000001, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005074632, "min": 0.0005074632, "max": 0.021904204, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.818181818181817, "min": 4.545454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1136.0, "min": 100.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.818181818181817, "min": 4.545454545454546, "max": 25.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1136.0, "min": 100.0, "max": 1406.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684800213", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1684800702" }, "total": 489.64451215400004, "count": 1, "self": 0.791335937000099, "children": { "run_training.setup": { "total": 0.06397809800000687, "count": 1, "self": 0.06397809800000687 }, "TrainerController.start_learning": { "total": 488.78919811899993, "count": 1, "self": 0.5855051090049983, "children": { "TrainerController._reset_env": { "total": 5.076384251000036, "count": 1, "self": 5.076384251000036 }, "TrainerController.advance": { "total": 482.8961280199949, "count": 17758, "self": 0.2937743290030994, "children": { "env_step": { "total": 482.6023536909918, "count": 17758, "self": 352.62906332699896, "children": { "SubprocessEnvManager._take_step": { "total": 129.69049512899733, "count": 17758, "self": 1.8027949619893207, "children": { "TorchPolicy.evaluate": { "total": 127.887700167008, "count": 17758, "self": 127.887700167008 } } }, "workers": { "total": 0.28279523499548986, "count": 17758, "self": 0.0, "children": { "worker_root": { "total": 486.88140983100345, "count": 17758, "is_parallel": true, "self": 228.5440531170055, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003403717000026063, "count": 1, "is_parallel": true, "self": 0.0009043510000310562, "children": { "_process_rank_one_or_two_observation": { "total": 0.002499365999995007, "count": 10, "is_parallel": true, "self": 0.002499365999995007 } } }, "UnityEnvironment.step": { "total": 0.12036650600003895, "count": 1, "is_parallel": true, "self": 0.0006001710000873572, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000554515999965588, "count": 1, "is_parallel": true, "self": 0.000554515999965588 }, "communicator.exchange": { "total": 0.11297735400000875, "count": 1, "is_parallel": true, "self": 0.11297735400000875 }, "steps_from_proto": { "total": 0.006234464999977263, "count": 1, "is_parallel": true, "self": 0.0013472159999423639, "children": { "_process_rank_one_or_two_observation": { "total": 0.004887249000034899, "count": 10, "is_parallel": true, "self": 0.004887249000034899 } } } } } } }, "UnityEnvironment.step": { "total": 258.33735671399796, "count": 17757, "is_parallel": true, "self": 9.931823146993338, "children": { "UnityEnvironment._generate_step_input": { "total": 5.587392548996036, "count": 17757, "is_parallel": true, "self": 5.587392548996036 }, "communicator.exchange": { "total": 206.69902286500394, "count": 17757, "is_parallel": true, "self": 206.69902286500394 }, "steps_from_proto": { "total": 36.11911815300465, "count": 17757, "is_parallel": true, "self": 7.059555132006551, "children": { "_process_rank_one_or_two_observation": { "total": 29.059563020998098, "count": 177570, "is_parallel": true, "self": 29.059563020998098 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016971100001228479, "count": 1, "self": 0.00016971100001228479, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.99355130495525, "count": 462471, "is_parallel": true, "self": 10.77299956690166, "children": { "process_trajectory": { "total": 262.6289624830535, "count": 462471, "is_parallel": true, "self": 260.8337015720536, "children": { "RLTrainer._checkpoint": { "total": 1.7952609109999003, "count": 4, "is_parallel": true, "self": 1.7952609109999003 } } }, "_update_policy": { "total": 205.5915892550001, "count": 88, "is_parallel": true, "self": 78.40621398899913, "children": { "TorchPPOOptimizer.update": { "total": 127.18537526600096, "count": 4485, "is_parallel": true, "self": 127.18537526600096 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23101102800001172, "count": 1, "self": 0.0018925560000297992, "children": { "RLTrainer._checkpoint": { "total": 0.22911847199998192, "count": 1, "self": 0.22911847199998192 } } } } } } }