{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3121693730354309, "min": 0.3121693730354309, "max": 1.494356393814087, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9310.1396484375, "min": 9310.1396484375, "max": 45332.796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5460474491119385, "min": -0.10521982610225677, "max": 0.5675005316734314, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.61700439453125, "min": -25.252758026123047, "max": 156.06265258789062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019154032692313194, "min": -0.013546914793550968, "max": 0.22385480999946594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.248205184936523, "min": -3.7118546962738037, "max": 53.725154876708984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0684585649207639, "min": 0.06426962848999644, "max": 0.07364016054050478, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9584199088906946, "min": 0.5096072869318228, "max": 1.0589523554275122, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01521236711622415, "min": 0.0010843866715020693, "max": 0.015836375679923333, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2129731396271381, "min": 0.007590706700514486, "max": 0.23617602254243514, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.334218983864287e-06, "min": 7.334218983864287e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010267906577410002, "min": 0.00010267906577410002, "max": 0.0036335650888117, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244470714285715, "min": 0.10244470714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342259000000002, "min": 1.3691136000000002, "max": 2.6111883000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002542262435714287, "min": 0.0002542262435714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003559167410000001, "min": 0.003559167410000001, "max": 0.12113771117000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011806068010628223, "min": 0.011806068010628223, "max": 0.3712029755115509, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16528494656085968, "min": 0.16528494656085968, "max": 2.5984208583831787, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 350.1011235955056, "min": 322.40909090909093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31159.0, "min": 15984.0, "max": 32440.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.540475534896056, "min": -1.0000000521540642, "max": 1.6548590670255097, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.64279814064503, "min": -32.000001668930054, "max": 145.62759789824486, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.540475534896056, "min": -1.0000000521540642, "max": 1.6548590670255097, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.64279814064503, "min": -32.000001668930054, "max": 145.62759789824486, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04285971156083785, "min": 0.04285971156083785, "max": 7.626113867387176, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.857374040475406, "min": 3.8192111155367456, "max": 122.01782187819481, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709278140", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709282011" }, "total": 3870.8012141460003, "count": 1, "self": 1.3676986020000186, "children": { "run_training.setup": { "total": 0.11622935300010795, "count": 1, "self": 0.11622935300010795 }, "TrainerController.start_learning": { "total": 3869.317286191, "count": 1, "self": 2.862807804001932, "children": { "TrainerController._reset_env": { "total": 4.33074100299973, "count": 1, "self": 4.33074100299973 }, "TrainerController.advance": { "total": 3862.0150585129977, "count": 63908, "self": 3.2245753821612197, "children": { "env_step": { "total": 2593.1195845118946, "count": 63908, "self": 2388.193954513845, "children": { "SubprocessEnvManager._take_step": { "total": 203.15541990603242, "count": 63908, "self": 9.540404454964573, "children": { "TorchPolicy.evaluate": { "total": 193.61501545106785, "count": 62554, "self": 193.61501545106785 } } }, "workers": { "total": 1.7702100920173507, "count": 63908, "self": 0.0, "children": { "worker_root": { "total": 3861.2402000161037, "count": 63908, "is_parallel": true, "self": 1686.3364013402038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006119706999925256, "count": 1, "is_parallel": true, "self": 0.0021786889997201797, "children": { "_process_rank_one_or_two_observation": { "total": 0.0039410180002050765, "count": 8, "is_parallel": true, "self": 0.0039410180002050765 } } }, "UnityEnvironment.step": { "total": 0.08104462600022089, "count": 1, "is_parallel": true, "self": 0.0008130140008688613, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007003409996286791, "count": 1, "is_parallel": true, "self": 0.0007003409996286791 }, "communicator.exchange": { "total": 0.07713505399988208, "count": 1, "is_parallel": true, "self": 0.07713505399988208 }, "steps_from_proto": { "total": 0.002396216999841272, "count": 1, "is_parallel": true, "self": 0.0005023000003347988, "children": { "_process_rank_one_or_two_observation": { "total": 0.001893916999506473, "count": 8, "is_parallel": true, "self": 0.001893916999506473 } } } } } } }, "UnityEnvironment.step": { "total": 2174.9037986759, "count": 63907, "is_parallel": true, "self": 54.52567161098659, "children": { "UnityEnvironment._generate_step_input": { "total": 33.674354898819274, "count": 63907, "is_parallel": true, "self": 33.674354898819274 }, "communicator.exchange": { "total": 1941.8240554060785, "count": 63907, "is_parallel": true, "self": 1941.8240554060785 }, "steps_from_proto": { "total": 144.87971676001553, "count": 63907, "is_parallel": true, "self": 32.381907472821695, "children": { "_process_rank_one_or_two_observation": { "total": 112.49780928719383, "count": 511256, "is_parallel": true, "self": 112.49780928719383 } } } } } } } } } } }, "trainer_advance": { "total": 1265.670898618942, "count": 63908, "self": 6.179756975932833, "children": { "process_trajectory": { "total": 201.94388196501723, "count": 63908, "self": 201.68398080901852, "children": { "RLTrainer._checkpoint": { "total": 0.2599011559987048, "count": 2, "self": 0.2599011559987048 } } }, "_update_policy": { "total": 1057.5472596779919, "count": 452, "self": 408.5615355900186, "children": { "TorchPPOOptimizer.update": { "total": 648.9857240879733, "count": 22815, "self": 648.9857240879733 } } } } } } }, "trainer_threads": { "total": 1.1100000847363845e-06, "count": 1, "self": 1.1100000847363845e-06 }, "TrainerController._save_models": { "total": 0.10867776100076298, "count": 1, "self": 0.004713486000582634, "children": { "RLTrainer._checkpoint": { "total": 0.10396427500018035, "count": 1, "self": 0.10396427500018035 } } } } } } }