{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5357014536857605, "min": 0.4885501265525818, "max": 1.3672888278961182, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16105.3291015625, "min": 14633.0537109375, "max": 41478.07421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4859307110309601, "min": -0.1279352754354477, "max": 0.48969095945358276, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.74349975585938, "min": -30.832401275634766, "max": 131.91815185546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.1239407062530518, "min": -0.07054843753576279, "max": 1.1239407062530518, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 300.0921630859375, "min": -19.259723663330078, "max": 300.0921630859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06895625416267043, "min": 0.06491572559960851, "max": 0.077766173912679, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0343438124400564, "min": 0.5111360454767268, "max": 1.0504675143553566, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.14470961635104482, "min": 0.0006092779717312957, "max": 0.14470961635104482, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 2.1706442452656725, "min": 0.006702057689044252, "max": 2.1706442452656725, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.469717510126672e-06, "min": 7.469717510126672e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011204576265190008, "min": 0.00011204576265190008, "max": 0.003382917272361, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248987333333334, "min": 0.10248987333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373481000000002, "min": 1.3886848, "max": 2.527639, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025873834600000014, "min": 0.00025873834600000014, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003881075190000002, "min": 0.003881075190000002, "max": 0.11279113609999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01273680105805397, "min": 0.01273680105805397, "max": 0.595973014831543, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19105201959609985, "min": 0.1810784786939621, "max": 4.171811103820801, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 388.9078947368421, "min": 381.28205128205127, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29557.0, "min": 15984.0, "max": 32166.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5321262970958884, "min": -1.0000000521540642, "max": 1.5321262970958884, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.44159857928753, "min": -31.99920167028904, "max": 116.44159857928753, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5321262970958884, "min": -1.0000000521540642, "max": 1.5321262970958884, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.44159857928753, "min": -31.99920167028904, "max": 116.44159857928753, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05111637746219793, "min": 0.05111637746219793, "max": 11.873138459399343, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8848446871270426, "min": 3.884203913505189, "max": 189.97021535038948, "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": "1735365331", "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 Training1 --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": "1735367522" }, "total": 2190.8134054539996, "count": 1, "self": 0.5277503719999004, "children": { "run_training.setup": { "total": 0.05583379699987745, "count": 1, "self": 0.05583379699987745 }, "TrainerController.start_learning": { "total": 2190.229821285, "count": 1, "self": 1.3656889760213744, "children": { "TrainerController._reset_env": { "total": 2.258067975999893, "count": 1, "self": 2.258067975999893 }, "TrainerController.advance": { "total": 2186.5242351489787, "count": 63578, "self": 1.428900129941212, "children": { "env_step": { "total": 1516.9090599969984, "count": 63578, "self": 1366.8656240940095, "children": { "SubprocessEnvManager._take_step": { "total": 149.1971187909851, "count": 63578, "self": 4.548870795938456, "children": { "TorchPolicy.evaluate": { "total": 144.64824799504663, "count": 62558, "self": 144.64824799504663 } } }, "workers": { "total": 0.8463171120038169, "count": 63578, "self": 0.0, "children": { "worker_root": { "total": 2185.2515501240364, "count": 63578, "is_parallel": true, "self": 938.1058184230296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021518030000606814, "count": 1, "is_parallel": true, "self": 0.0007019209997451981, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014498820003154833, "count": 8, "is_parallel": true, "self": 0.0014498820003154833 } } }, "UnityEnvironment.step": { "total": 0.04895375699993565, "count": 1, "is_parallel": true, "self": 0.00211787600005664, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004745209998873179, "count": 1, "is_parallel": true, "self": 0.0004745209998873179 }, "communicator.exchange": { "total": 0.0447163090000231, "count": 1, "is_parallel": true, "self": 0.0447163090000231 }, "steps_from_proto": { "total": 0.0016450509999685892, "count": 1, "is_parallel": true, "self": 0.0003625850001753861, "children": { "_process_rank_one_or_two_observation": { "total": 0.001282465999793203, "count": 8, "is_parallel": true, "self": 0.001282465999793203 } } } } } } }, "UnityEnvironment.step": { "total": 1247.1457317010068, "count": 63577, "is_parallel": true, "self": 33.262665535929955, "children": { "UnityEnvironment._generate_step_input": { "total": 22.671067043075027, "count": 63577, "is_parallel": true, "self": 22.671067043075027 }, "communicator.exchange": { "total": 1095.2457668710263, "count": 63577, "is_parallel": true, "self": 1095.2457668710263 }, "steps_from_proto": { "total": 95.96623225097551, "count": 63577, "is_parallel": true, "self": 19.42191158590731, "children": { "_process_rank_one_or_two_observation": { "total": 76.5443206650682, "count": 508616, "is_parallel": true, "self": 76.5443206650682 } } } } } } } } } } }, "trainer_advance": { "total": 668.1862750220394, "count": 63578, "self": 2.639867959978119, "children": { "process_trajectory": { "total": 127.43863318106514, "count": 63578, "self": 127.19605569106534, "children": { "RLTrainer._checkpoint": { "total": 0.24257748999980322, "count": 2, "self": 0.24257748999980322 } } }, "_update_policy": { "total": 538.1077738809961, "count": 448, "self": 301.5329312819749, "children": { "TorchPPOOptimizer.update": { "total": 236.57484259902117, "count": 22812, "self": 236.57484259902117 } } } } } } }, "trainer_threads": { "total": 1.3359999684325885e-06, "count": 1, "self": 1.3359999684325885e-06 }, "TrainerController._save_models": { "total": 0.08182784800010268, "count": 1, "self": 0.0015451620001840638, "children": { "RLTrainer._checkpoint": { "total": 0.08028268599991861, "count": 1, "self": 0.08028268599991861 } } } } } } }