{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4789277911186218, "min": 0.4567798972129822, "max": 1.493379831314087, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14306.53125, "min": 13710.705078125, "max": 45303.171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.156187042593956, "min": -0.1038445234298706, "max": 0.15641452372074127, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 39.20294952392578, "min": -24.982479095458984, "max": 39.20294952392578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0020229294896125793, "min": 0.0020229294896125793, "max": 0.3120591640472412, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.5077552795410156, "min": 0.5077552795410156, "max": 73.95802307128906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06981141406074896, "min": 0.06482777008981509, "max": 0.07376855688787709, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0471712109112346, "min": 0.476110151833413, "max": 1.0471712109112346, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011120647125324085, "min": 0.0007657034386159787, "max": 0.011120647125324085, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16680970687986127, "min": 0.007609752863259176, "max": 0.16680970687986127, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.474217508626667e-06, "min": 7.474217508626667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001121132626294, "min": 0.0001121132626294, "max": 0.0035072351309216997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249137333333334, "min": 0.10249137333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373706000000003, "min": 1.3691136000000002, "max": 2.569078300000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258888196, "min": 0.000258888196, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00388332294, "min": 0.00388332294, "max": 0.11693092217, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013961868360638618, "min": 0.013948006555438042, "max": 0.44069403409957886, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20942802727222443, "min": 0.19527208805084229, "max": 3.0848581790924072, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 665.7173913043479, "min": 665.7173913043479, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30623.0, "min": 15984.0, "max": 32336.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.812365185469389, "min": -1.0000000521540642, "max": 0.812365185469389, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 37.36879853159189, "min": -32.000001668930054, "max": 37.36879853159189, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.812365185469389, "min": -1.0000000521540642, "max": 0.812365185469389, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 37.36879853159189, "min": -32.000001668930054, "max": 37.36879853159189, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09475868726250432, "min": 0.09475868726250432, "max": 9.12141172029078, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.358899614075199, "min": 4.132417161308695, "max": 145.94258752465248, "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": "1743513556", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743515546" }, "total": 1989.6591349689998, "count": 1, "self": 0.7427212159996088, "children": { "run_training.setup": { "total": 0.037944934999984525, "count": 1, "self": 0.037944934999984525 }, "TrainerController.start_learning": { "total": 1988.878468818, "count": 1, "self": 1.2708240650110838, "children": { "TrainerController._reset_env": { "total": 3.829117714000006, "count": 1, "self": 3.829117714000006 }, "TrainerController.advance": { "total": 1983.6834362239888, "count": 63244, "self": 1.3471865479989447, "children": { "env_step": { "total": 1313.056961843982, "count": 63244, "self": 1166.41025271399, "children": { "SubprocessEnvManager._take_step": { "total": 145.9260778480134, "count": 63244, "self": 4.418740220968857, "children": { "TorchPolicy.evaluate": { "total": 141.50733762704454, "count": 62568, "self": 141.50733762704454 } } }, "workers": { "total": 0.7206312819784557, "count": 63244, "self": 0.0, "children": { "worker_root": { "total": 1984.4947825860197, "count": 63244, "is_parallel": true, "self": 922.2681450270554, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053213600000390215, "count": 1, "is_parallel": true, "self": 0.0035178290001454116, "children": { "_process_rank_one_or_two_observation": { "total": 0.00180353099989361, "count": 8, "is_parallel": true, "self": 0.00180353099989361 } } }, "UnityEnvironment.step": { "total": 0.048582285999998476, "count": 1, "is_parallel": true, "self": 0.0005956889999652049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046176199998626544, "count": 1, "is_parallel": true, "self": 0.00046176199998626544 }, "communicator.exchange": { "total": 0.045807532000026185, "count": 1, "is_parallel": true, "self": 0.045807532000026185 }, "steps_from_proto": { "total": 0.00171730300002082, "count": 1, "is_parallel": true, "self": 0.0004950490001078833, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012222539999129367, "count": 8, "is_parallel": true, "self": 0.0012222539999129367 } } } } } } }, "UnityEnvironment.step": { "total": 1062.2266375589643, "count": 63243, "is_parallel": true, "self": 31.41921442998455, "children": { "UnityEnvironment._generate_step_input": { "total": 22.381173736999415, "count": 63243, "is_parallel": true, "self": 22.381173736999415 }, "communicator.exchange": { "total": 916.7867777569652, "count": 63243, "is_parallel": true, "self": 916.7867777569652 }, "steps_from_proto": { "total": 91.63947163501496, "count": 63243, "is_parallel": true, "self": 17.98900764903209, "children": { "_process_rank_one_or_two_observation": { "total": 73.65046398598287, "count": 505944, "is_parallel": true, "self": 73.65046398598287 } } } } } } } } } } }, "trainer_advance": { "total": 669.2792878320079, "count": 63244, "self": 2.374071500027526, "children": { "process_trajectory": { "total": 123.44113914997854, "count": 63244, "self": 123.1559100419787, "children": { "RLTrainer._checkpoint": { "total": 0.28522910799983947, "count": 2, "self": 0.28522910799983947 } } }, "_update_policy": { "total": 543.4640771820018, "count": 444, "self": 300.30302516500745, "children": { "TorchPPOOptimizer.update": { "total": 243.16105201699435, "count": 22809, "self": 243.16105201699435 } } } } } } }, "trainer_threads": { "total": 8.780002644925844e-07, "count": 1, "self": 8.780002644925844e-07 }, "TrainerController._save_models": { "total": 0.09508993700001156, "count": 1, "self": 0.0014623689999098133, "children": { "RLTrainer._checkpoint": { "total": 0.09362756800010175, "count": 1, "self": 0.09362756800010175 } } } } } } }