{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6115803122520447, "min": 0.6094377040863037, "max": 1.4565856456756592, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18376.765625, "min": 18185.62109375, "max": 44186.98046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989940.0, "min": 29952.0, "max": 989940.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2192930281162262, "min": -0.09305952489376068, "max": 0.2192930281162262, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.139015197753906, "min": -22.427345275878906, "max": 56.139015197753906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.08302832394838333, "min": -0.08302832394838333, "max": 0.662807285785675, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -21.255250930786133, "min": -21.255250930786133, "max": 157.0853271484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06805212741297198, "min": 0.06483253724299562, "max": 0.07381875635881606, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9527297837816077, "min": 0.5144852739425935, "max": 1.0490281150753922, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017257428631072026, "min": 0.0003259546251754348, "max": 0.017257428631072026, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24160400083500838, "min": 0.002933591626578913, "max": 0.24160400083500838, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.637004597221431e-06, "min": 7.637004597221431e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010691806436110002, "min": 0.00010691806436110002, "max": 0.0032547161150946998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254563571428574, "min": 0.10254563571428574, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356389000000003, "min": 1.3886848, "max": 2.4423938, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026430900785714295, "min": 0.00026430900785714295, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003700326110000001, "min": 0.003700326110000001, "max": 0.10851203947000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01597723551094532, "min": 0.01597723551094532, "max": 0.6487232446670532, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22368130087852478, "min": 0.22368130087852478, "max": 4.541062831878662, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 678.7045454545455, "min": 589.4509803921569, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29863.0, "min": 15984.0, "max": 33910.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0030090587044305, "min": -1.0000000521540642, "max": 1.0030090587044305, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.13239858299494, "min": -31.998401656746864, "max": 45.929598830640316, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0030090587044305, "min": -1.0000000521540642, "max": 1.0030090587044305, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.13239858299494, "min": -31.998401656746864, "max": 45.929598830640316, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11248435904483566, "min": 0.10194601255668954, "max": 13.45548995770514, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.9493117979727685, "min": 4.559003848757129, "max": 215.28783932328224, "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": "1689803019", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.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": "1689805113" }, "total": 2093.704646631, "count": 1, "self": 0.4839880209997318, "children": { "run_training.setup": { "total": 0.048760985000171786, "count": 1, "self": 0.048760985000171786 }, "TrainerController.start_learning": { "total": 2093.171897625, "count": 1, "self": 1.3180764618987268, "children": { "TrainerController._reset_env": { "total": 5.3561736360002214, "count": 1, "self": 5.3561736360002214 }, "TrainerController.advance": { "total": 2086.4049171281017, "count": 63331, "self": 1.3437824670663758, "children": { "env_step": { "total": 1424.053160464035, "count": 63331, "self": 1319.0801552350576, "children": { "SubprocessEnvManager._take_step": { "total": 104.16805083692452, "count": 63331, "self": 4.672769805818007, "children": { "TorchPolicy.evaluate": { "total": 99.49528103110652, "count": 62563, "self": 99.49528103110652 } } }, "workers": { "total": 0.8049543920528777, "count": 63331, "self": 0.0, "children": { "worker_root": { "total": 2088.749662699087, "count": 63331, "is_parallel": true, "self": 879.8682464541143, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002594572999896627, "count": 1, "is_parallel": true, "self": 0.0007228780000332335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018716949998633936, "count": 8, "is_parallel": true, "self": 0.0018716949998633936 } } }, "UnityEnvironment.step": { "total": 0.050544313000045804, "count": 1, "is_parallel": true, "self": 0.0005786550004813762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000497584999720857, "count": 1, "is_parallel": true, "self": 0.000497584999720857 }, "communicator.exchange": { "total": 0.047675266999704036, "count": 1, "is_parallel": true, "self": 0.047675266999704036 }, "steps_from_proto": { "total": 0.0017928060001395352, "count": 1, "is_parallel": true, "self": 0.00036497400014923187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014278319999903033, "count": 8, "is_parallel": true, "self": 0.0014278319999903033 } } } } } } }, "UnityEnvironment.step": { "total": 1208.8814162449726, "count": 63330, "is_parallel": true, "self": 33.70078335995504, "children": { "UnityEnvironment._generate_step_input": { "total": 22.386825297926407, "count": 63330, "is_parallel": true, "self": 22.386825297926407 }, "communicator.exchange": { "total": 1053.424484299027, "count": 63330, "is_parallel": true, "self": 1053.424484299027 }, "steps_from_proto": { "total": 99.36932328806415, "count": 63330, "is_parallel": true, "self": 19.913307017788156, "children": { "_process_rank_one_or_two_observation": { "total": 79.456016270276, "count": 506640, "is_parallel": true, "self": 79.456016270276 } } } } } } } } } } }, "trainer_advance": { "total": 661.0079741970003, "count": 63331, "self": 2.513784414975362, "children": { "process_trajectory": { "total": 108.45604083902708, "count": 63331, "self": 108.25097340402681, "children": { "RLTrainer._checkpoint": { "total": 0.2050674350002737, "count": 2, "self": 0.2050674350002737 } } }, "_update_policy": { "total": 550.0381489429979, "count": 446, "self": 362.0209358440143, "children": { "TorchPPOOptimizer.update": { "total": 188.01721309898358, "count": 22785, "self": 188.01721309898358 } } } } } } }, "trainer_threads": { "total": 1.0499998097657226e-06, "count": 1, "self": 1.0499998097657226e-06 }, "TrainerController._save_models": { "total": 0.0927293489994554, "count": 1, "self": 0.0013048450000496814, "children": { "RLTrainer._checkpoint": { "total": 0.09142450399940572, "count": 1, "self": 0.09142450399940572 } } } } } } }