{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38364672660827637, "min": 0.38364672660827637, "max": 1.459175944328308, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11490.986328125, "min": 11490.986328125, "max": 44265.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6232269406318665, "min": -0.12185036391019821, "max": 0.6492074131965637, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.75, "min": -29.365938186645508, "max": 181.778076171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006430040113627911, "min": -0.014972793869674206, "max": 0.5385123491287231, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.8132712841033936, "min": -3.9078991413116455, "max": 127.62742614746094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06903137952446871, "min": 0.06533447390318876, "max": 0.07313739010307739, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9664393133425618, "min": 0.5037453645270253, "max": 1.0635975119749121, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014940131267177916, "min": 0.0013474361503178396, "max": 0.01710394765692241, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20916183774049082, "min": 0.018425317096706535, "max": 0.24555822061180757, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.51511892356429e-06, "min": 7.51511892356429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010521166492990006, "min": 0.00010521166492990006, "max": 0.0035087264304246, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250500714285715, "min": 0.10250500714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350701000000001, "min": 1.3886848, "max": 2.5695754, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026025021357142873, "min": 0.00026025021357142873, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003643502990000002, "min": 0.003643502990000002, "max": 0.11698058246000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012131420895457268, "min": 0.012131420895457268, "max": 0.720535397529602, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16983988881111145, "min": 0.16983988881111145, "max": 5.043747901916504, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 322.9789473684211, "min": 287.25, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30683.0, "min": 15984.0, "max": 32190.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.613842091748589, "min": -1.0000000521540642, "max": 1.7145463741317237, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.31499871611595, "min": -30.22120165079832, "max": 171.56659818440676, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.613842091748589, "min": -1.0000000521540642, "max": 1.7145463741317237, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.31499871611595, "min": -30.22120165079832, "max": 171.56659818440676, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040745640572430075, "min": 0.03720512080979029, "max": 14.474275099113584, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.870835854380857, "min": 3.6088967185496585, "max": 231.58840158581734, "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": "1739076643", "python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739078916" }, "total": 2272.8826874469996, "count": 1, "self": 0.5268317149998438, "children": { "run_training.setup": { "total": 0.018968414000028133, "count": 1, "self": 0.018968414000028133 }, "TrainerController.start_learning": { "total": 2272.3368873179998, "count": 1, "self": 1.4268662989629775, "children": { "TrainerController._reset_env": { "total": 2.554789932999938, "count": 1, "self": 2.554789932999938 }, "TrainerController.advance": { "total": 2268.266272111037, "count": 63936, "self": 1.4746662989577999, "children": { "env_step": { "total": 1573.5335474690655, "count": 63936, "self": 1414.928939595101, "children": { "SubprocessEnvManager._take_step": { "total": 157.7747828600218, "count": 63936, "self": 4.770811132075778, "children": { "TorchPolicy.evaluate": { "total": 153.003971727946, "count": 62551, "self": 153.003971727946 } } }, "workers": { "total": 0.8298250139428092, "count": 63936, "self": 0.0, "children": { "worker_root": { "total": 2267.1156505549857, "count": 63936, "is_parallel": true, "self": 967.3725625719514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002021134999949936, "count": 1, "is_parallel": true, "self": 0.0006381190003139636, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013830159996359725, "count": 8, "is_parallel": true, "self": 0.0013830159996359725 } } }, "UnityEnvironment.step": { "total": 0.08994533300005969, "count": 1, "is_parallel": true, "self": 0.0005137139999078499, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004639890000817104, "count": 1, "is_parallel": true, "self": 0.0004639890000817104 }, "communicator.exchange": { "total": 0.08731925100005355, "count": 1, "is_parallel": true, "self": 0.08731925100005355 }, "steps_from_proto": { "total": 0.0016483790000165754, "count": 1, "is_parallel": true, "self": 0.00035842799979945994, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012899510002171155, "count": 8, "is_parallel": true, "self": 0.0012899510002171155 } } } } } } }, "UnityEnvironment.step": { "total": 1299.7430879830342, "count": 63935, "is_parallel": true, "self": 31.532362687061095, "children": { "UnityEnvironment._generate_step_input": { "total": 22.92380315401124, "count": 63935, "is_parallel": true, "self": 22.92380315401124 }, "communicator.exchange": { "total": 1147.5995340329728, "count": 63935, "is_parallel": true, "self": 1147.5995340329728 }, "steps_from_proto": { "total": 97.68738810898913, "count": 63935, "is_parallel": true, "self": 19.866832524058736, "children": { "_process_rank_one_or_two_observation": { "total": 77.82055558493039, "count": 511480, "is_parallel": true, "self": 77.82055558493039 } } } } } } } } } } }, "trainer_advance": { "total": 693.2580583430135, "count": 63936, "self": 2.6799836619782127, "children": { "process_trajectory": { "total": 132.26090501903354, "count": 63936, "self": 131.86275718103343, "children": { "RLTrainer._checkpoint": { "total": 0.39814783800011355, "count": 2, "self": 0.39814783800011355 } } }, "_update_policy": { "total": 558.3171696620018, "count": 453, "self": 309.53836960001513, "children": { "TorchPPOOptimizer.update": { "total": 248.77880006198666, "count": 22773, "self": 248.77880006198666 } } } } } } }, "trainer_threads": { "total": 9.54999904934084e-07, "count": 1, "self": 9.54999904934084e-07 }, "TrainerController._save_models": { "total": 0.0889580200000637, "count": 1, "self": 0.0015613450000273588, "children": { "RLTrainer._checkpoint": { "total": 0.08739667500003634, "count": 1, "self": 0.08739667500003634 } } } } } } }