{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.574554443359375, "min": 0.574554443359375, "max": 1.4881778955459595, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17052.775390625, "min": 17052.775390625, "max": 45145.36328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.563162088394165, "min": -0.0910487025976181, "max": 0.563162088394165, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.4327392578125, "min": -22.03378677368164, "max": 155.4327392578125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.12467113137245178, "min": -0.13161659240722656, "max": 0.3514404296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -34.40923309326172, "min": -35.40486145019531, "max": 83.2913818359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07107339050673459, "min": 0.06330698107145707, "max": 0.07408186435971482, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9950274670942841, "min": 0.5185730505180037, "max": 1.0367000888412197, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01616940419660837, "min": 0.0007501564969565384, "max": 0.018519008566467425, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22637165875251716, "min": 0.008251721466521922, "max": 0.25926611993054394, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.635247454950001e-06, "min": 7.635247454950001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010689346436930002, "min": 0.00010689346436930002, "max": 0.0035086205304599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254505000000001, "min": 0.10254505000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356307000000001, "min": 1.3886848, "max": 2.5695401, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000264250495, "min": 0.000264250495, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036995069300000006, "min": 0.0036995069300000006, "max": 0.11697705599, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007648668251931667, "min": 0.007648668251931667, "max": 0.3580719530582428, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1070813536643982, "min": 0.1070813536643982, "max": 2.5065035820007324, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.314606741573, "min": 329.314606741573, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29309.0, "min": 15984.0, "max": 33504.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.648368879655997, "min": -1.0000000521540642, "max": 1.648368879655997, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.35319916903973, "min": -30.358801662921906, "max": 148.35319916903973, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.648368879655997, "min": -1.0000000521540642, "max": 1.648368879655997, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.35319916903973, "min": -30.358801662921906, "max": 148.35319916903973, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026177742367953113, "min": 0.026177742367953113, "max": 6.980168289504945, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3559968131157802, "min": 2.3559968131157802, "max": 111.68269263207912, "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": "1734127595", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734129929" }, "total": 2333.5636120960003, "count": 1, "self": 0.5780463950000012, "children": { "run_training.setup": { "total": 0.05754078300014953, "count": 1, "self": 0.05754078300014953 }, "TrainerController.start_learning": { "total": 2332.928024918, "count": 1, "self": 1.5294582421242922, "children": { "TrainerController._reset_env": { "total": 6.2774709519999305, "count": 1, "self": 6.2774709519999305 }, "TrainerController.advance": { "total": 2325.0358456738754, "count": 63715, "self": 1.5516037508505178, "children": { "env_step": { "total": 1614.0539924190052, "count": 63715, "self": 1453.463504698062, "children": { "SubprocessEnvManager._take_step": { "total": 159.66487137302147, "count": 63715, "self": 4.721875491924948, "children": { "TorchPolicy.evaluate": { "total": 154.94299588109652, "count": 62561, "self": 154.94299588109652 } } }, "workers": { "total": 0.9256163479217321, "count": 63715, "self": 0.0, "children": { "worker_root": { "total": 2327.5153936739666, "count": 63715, "is_parallel": true, "self": 995.7588343289813, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002110785999775544, "count": 1, "is_parallel": true, "self": 0.0006689530009680311, "children": { "_process_rank_one_or_two_observation": { "total": 0.001441832998807513, "count": 8, "is_parallel": true, "self": 0.001441832998807513 } } }, "UnityEnvironment.step": { "total": 0.05138685500014617, "count": 1, "is_parallel": true, "self": 0.0005862230004822777, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042966999990312615, "count": 1, "is_parallel": true, "self": 0.00042966999990312615 }, "communicator.exchange": { "total": 0.048743414000000485, "count": 1, "is_parallel": true, "self": 0.048743414000000485 }, "steps_from_proto": { "total": 0.0016275479997602815, "count": 1, "is_parallel": true, "self": 0.00034151799945902894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012860300003012526, "count": 8, "is_parallel": true, "self": 0.0012860300003012526 } } } } } } }, "UnityEnvironment.step": { "total": 1331.7565593449854, "count": 63714, "is_parallel": true, "self": 35.15711671303961, "children": { "UnityEnvironment._generate_step_input": { "total": 23.43241907196716, "count": 63714, "is_parallel": true, "self": 23.43241907196716 }, "communicator.exchange": { "total": 1172.0102111670526, "count": 63714, "is_parallel": true, "self": 1172.0102111670526 }, "steps_from_proto": { "total": 101.15681239292599, "count": 63714, "is_parallel": true, "self": 20.582145362376195, "children": { "_process_rank_one_or_two_observation": { "total": 80.57466703054979, "count": 509712, "is_parallel": true, "self": 80.57466703054979 } } } } } } } } } } }, "trainer_advance": { "total": 709.4302495040197, "count": 63715, "self": 2.951239839067057, "children": { "process_trajectory": { "total": 136.603210146955, "count": 63715, "self": 136.21961644495514, "children": { "RLTrainer._checkpoint": { "total": 0.383593701999871, "count": 2, "self": 0.383593701999871 } } }, "_update_policy": { "total": 569.8757995179976, "count": 451, "self": 320.43056980103074, "children": { "TorchPPOOptimizer.update": { "total": 249.44522971696688, "count": 22788, "self": 249.44522971696688 } } } } } } }, "trainer_threads": { "total": 1.0390003808424808e-06, "count": 1, "self": 1.0390003808424808e-06 }, "TrainerController._save_models": { "total": 0.0852490110000872, "count": 1, "self": 0.0015210050005407538, "children": { "RLTrainer._checkpoint": { "total": 0.08372800599954644, "count": 1, "self": 0.08372800599954644 } } } } } } }