{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5585489273071289, "min": 0.5516825914382935, "max": 1.433143973350525, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16792.21484375, "min": 16362.4990234375, "max": 43475.85546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2760472297668457, "min": -0.10399471968412399, "max": 0.2844479978084564, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.49623107910156, "min": -24.95873260498047, "max": 74.24092864990234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002693533431738615, "min": 0.0005512988427653909, "max": 0.4077441990375519, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6976251602172852, "min": 0.13837601244449615, "max": 96.6353759765625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0701080114056822, "min": 0.06452763149247723, "max": 0.07518882900649933, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0516201710852329, "min": 0.5263218030454953, "max": 1.0516201710852329, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01172170010071972, "min": 0.00013222160973721026, "max": 0.012953916126069763, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17582550151079582, "min": 0.0018511025363209435, "max": 0.1813548257649767, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.550897483066671e-06, "min": 7.550897483066671e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011326346224600007, "min": 0.00011326346224600007, "max": 0.003374960575013199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251693333333334, "min": 0.10251693333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537754, "min": 1.3886848, "max": 2.4850783, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002614416400000002, "min": 0.0002614416400000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003921624600000003, "min": 0.003921624600000003, "max": 0.11251618132, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016451720148324966, "min": 0.016451720148324966, "max": 0.5526224374771118, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2467758059501648, "min": 0.237635537981987, "max": 3.8683571815490723, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 585.0, "min": 531.574074074074, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32760.0, "min": 15984.0, "max": 33022.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1622181549668311, "min": -1.0000000521540642, "max": 1.2461481243371964, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 63.921998523175716, "min": -30.996601596474648, "max": 67.2919987142086, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1622181549668311, "min": -1.0000000521540642, "max": 1.2461481243371964, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 63.921998523175716, "min": -30.996601596474648, "max": 67.2919987142086, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09873100745661015, "min": 0.09448294828379639, "max": 11.09983042627573, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.430205410113558, "min": 5.102079207325005, "max": 177.59728682041168, "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": "1727189735", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727193096" }, "total": 3361.743825507, "count": 1, "self": 0.6578675920009118, "children": { "run_training.setup": { "total": 0.07461541999987276, "count": 1, "self": 0.07461541999987276 }, "TrainerController.start_learning": { "total": 3361.0113424949996, "count": 1, "self": 2.5310426508949604, "children": { "TrainerController._reset_env": { "total": 2.927751212999965, "count": 1, "self": 2.927751212999965 }, "TrainerController.advance": { "total": 3355.470109205105, "count": 63355, "self": 2.59331382413302, "children": { "env_step": { "total": 2173.3011444348886, "count": 63355, "self": 1999.6405767949873, "children": { "SubprocessEnvManager._take_step": { "total": 172.17572298587265, "count": 63355, "self": 7.694169884903204, "children": { "TorchPolicy.evaluate": { "total": 164.48155310096945, "count": 62567, "self": 164.48155310096945 } } }, "workers": { "total": 1.4848446540286204, "count": 63355, "self": 0.0, "children": { "worker_root": { "total": 3353.3496659049983, "count": 63355, "is_parallel": true, "self": 1547.5990844539974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025841260001016053, "count": 1, "is_parallel": true, "self": 0.0008530700001756486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017310559999259567, "count": 8, "is_parallel": true, "self": 0.0017310559999259567 } } }, "UnityEnvironment.step": { "total": 0.10892575599996235, "count": 1, "is_parallel": true, "self": 0.0007799439999871538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005323820000739943, "count": 1, "is_parallel": true, "self": 0.0005323820000739943 }, "communicator.exchange": { "total": 0.10545368799989774, "count": 1, "is_parallel": true, "self": 0.10545368799989774 }, "steps_from_proto": { "total": 0.0021597420000034617, "count": 1, "is_parallel": true, "self": 0.0003908269998191827, "children": { "_process_rank_one_or_two_observation": { "total": 0.001768915000184279, "count": 8, "is_parallel": true, "self": 0.001768915000184279 } } } } } } }, "UnityEnvironment.step": { "total": 1805.750581451001, "count": 63354, "is_parallel": true, "self": 51.9025177649944, "children": { "UnityEnvironment._generate_step_input": { "total": 31.270352153946988, "count": 63354, "is_parallel": true, "self": 31.270352153946988 }, "communicator.exchange": { "total": 1591.9770203299545, "count": 63354, "is_parallel": true, "self": 1591.9770203299545 }, "steps_from_proto": { "total": 130.60069120210505, "count": 63354, "is_parallel": true, "self": 28.673627834974923, "children": { "_process_rank_one_or_two_observation": { "total": 101.92706336713013, "count": 506832, "is_parallel": true, "self": 101.92706336713013 } } } } } } } } } } }, "trainer_advance": { "total": 1179.5756509460837, "count": 63355, "self": 4.788921217142843, "children": { "process_trajectory": { "total": 173.948135474938, "count": 63355, "self": 173.7613137749379, "children": { "RLTrainer._checkpoint": { "total": 0.18682170000010956, "count": 2, "self": 0.18682170000010956 } } }, "_update_policy": { "total": 1000.8385942540028, "count": 449, "self": 395.6732891570307, "children": { "TorchPPOOptimizer.update": { "total": 605.1653050969721, "count": 22770, "self": 605.1653050969721 } } } } } } }, "trainer_threads": { "total": 1.0510002539376728e-06, "count": 1, "self": 1.0510002539376728e-06 }, "TrainerController._save_models": { "total": 0.08243837499958317, "count": 1, "self": 0.0021922239993728, "children": { "RLTrainer._checkpoint": { "total": 0.08024615100021038, "count": 1, "self": 0.08024615100021038 } } } } } } }