{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25953876972198486, "min": 0.2554902136325836, "max": 1.4421803951263428, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 7790.3154296875, "min": 7681.05810546875, "max": 43749.984375, "count": 50 }, "Pyramids.Step.mean": { "value": 1499973.0, "min": 29952.0, "max": 1499973.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499973.0, "min": 29952.0, "max": 1499973.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8143863081932068, "min": -0.09743756055831909, "max": 0.851116955280304, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.87274169921875, "min": -23.482452392578125, "max": 258.73956298828125, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03962195664644241, "min": 0.021022958680987358, "max": 0.3204623758792877, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.767721176147461, "min": 6.096657752990723, "max": 76.86979675292969, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06989702922319772, "min": 0.06551994576186713, "max": 0.07377703284873957, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9785584091247681, "min": 0.49282712330650297, "max": 1.0799011346506293, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014080626318380902, "min": 0.0012980103475642945, "max": 0.015892312451753588, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19712876845733263, "min": 0.018172144865900124, "max": 0.23813491165478184, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00015150425664145476, "min": 0.00015150425664145476, "max": 0.00029838354339596195, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0021210595929803664, "min": 0.0020886848037717336, "max": 0.004011224062925333, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1505014023809524, "min": 0.1505014023809524, "max": 0.19946118095238097, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1070196333333335, "min": 1.3962282666666668, "max": 2.7824553, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.0050550900978571425, "min": 0.0050550900978571425, "max": 0.009946171977142856, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.07077126136999999, "min": 0.06962320384, "max": 0.1337137592, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.06995836645364761, "min": 0.05724186822772026, "max": 0.5387540459632874, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.979417085647583, "min": 0.8586280345916748, "max": 3.7712783813476562, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 222.828125, "min": 206.85507246376812, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28522.0, "min": 15984.0, "max": 32329.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7741317714369573, "min": -1.0000000521540642, "max": 1.793144920165988, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 228.8629985153675, "min": -30.168801687657833, "max": 247.45399898290634, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7741317714369573, "min": -1.0000000521540642, "max": 1.793144920165988, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 228.8629985153675, "min": -30.168801687657833, "max": 247.45399898290634, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.15992938654425973, "min": 0.15674080851528308, "max": 10.55444335564971, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 20.630890864209505, "min": 18.251696077990346, "max": 168.87109369039536, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674193654", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674196920" }, "total": 3266.271138237, "count": 1, "self": 0.35971407399983946, "children": { "run_training.setup": { "total": 0.09719678200008275, "count": 1, "self": 0.09719678200008275 }, "TrainerController.start_learning": { "total": 3265.814227381, "count": 1, "self": 1.8229607039829716, "children": { "TrainerController._reset_env": { "total": 5.929033473000118, "count": 1, "self": 5.929033473000118 }, "TrainerController.advance": { "total": 3257.9293664160164, "count": 98018, "self": 1.9323758699947575, "children": { "env_step": { "total": 2259.167900679028, "count": 98018, "self": 2105.5260272810283, "children": { "SubprocessEnvManager._take_step": { "total": 152.5071143779494, "count": 98018, "self": 6.392982578003284, "children": { "TorchPolicy.evaluate": { "total": 146.1141317999461, "count": 94796, "self": 49.09433555398596, "children": { "TorchPolicy.sample_actions": { "total": 97.01979624596015, "count": 94796, "self": 97.01979624596015 } } } } }, "workers": { "total": 1.1347590200505238, "count": 98017, "self": 0.0, "children": { "worker_root": { "total": 3259.662274534021, "count": 98017, "is_parallel": true, "self": 1299.533615427968, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017242639999039966, "count": 1, "is_parallel": true, "self": 0.000608542000009038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011157219998949586, "count": 8, "is_parallel": true, "self": 0.0011157219998949586 } } }, "UnityEnvironment.step": { "total": 0.04609433099994931, "count": 1, "is_parallel": true, "self": 0.0004747250002310466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004216329998598667, "count": 1, "is_parallel": true, "self": 0.0004216329998598667 }, "communicator.exchange": { "total": 0.04358322699999917, "count": 1, "is_parallel": true, "self": 0.04358322699999917 }, "steps_from_proto": { "total": 0.001614745999859224, "count": 1, "is_parallel": true, "self": 0.0004187790004834824, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011959669993757416, "count": 8, "is_parallel": true, "self": 0.0011959669993757416 } } } } } } }, "UnityEnvironment.step": { "total": 1960.128659106053, "count": 98016, "is_parallel": true, "self": 40.912380216932206, "children": { "UnityEnvironment._generate_step_input": { "total": 32.58134666600586, "count": 98016, "is_parallel": true, "self": 32.58134666600586 }, "communicator.exchange": { "total": 1741.3693985590874, "count": 98016, "is_parallel": true, "self": 1741.3693985590874 }, "steps_from_proto": { "total": 145.26553366402754, "count": 98016, "is_parallel": true, "self": 31.580711796222204, "children": { "_process_rank_one_or_two_observation": { "total": 113.68482186780534, "count": 784128, "is_parallel": true, "self": 113.68482186780534 } } } } } } } } } } }, "trainer_advance": { "total": 996.8290898669934, "count": 98017, "self": 3.5357743109927924, "children": { "process_trajectory": { "total": 216.91994799100848, "count": 98017, "self": 216.6499311080088, "children": { "RLTrainer._checkpoint": { "total": 0.2700168829996983, "count": 3, "self": 0.2700168829996983 } } }, "_update_policy": { "total": 776.3733675649921, "count": 700, "self": 302.0121001809605, "children": { "TorchPPOOptimizer.update": { "total": 474.36126738403163, "count": 34551, "self": 474.36126738403163 } } } } } } }, "trainer_threads": { "total": 1.2090004020137712e-06, "count": 1, "self": 1.2090004020137712e-06 }, "TrainerController._save_models": { "total": 0.1328655790002813, "count": 1, "self": 0.0019326189994899323, "children": { "RLTrainer._checkpoint": { "total": 0.13093296000079135, "count": 1, "self": 0.13093296000079135 } } } } } } }