| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.35295552015304565, |
| "min": 0.34132206439971924, |
| "max": 1.5460758209228516, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10549.134765625, |
| "min": 10272.4287109375, |
| "max": 46901.7578125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989927.0, |
| "min": 29967.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989927.0, |
| "min": 29967.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.3157421946525574, |
| "min": -0.1791788935661316, |
| "max": 0.3983370363712311, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 81.77722930908203, |
| "min": -42.64457702636719, |
| "max": 105.55931091308594, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.012032031081616879, |
| "min": -0.02581746131181717, |
| "max": 0.15964160859584808, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.1162960529327393, |
| "min": -6.609270095825195, |
| "max": 37.99470138549805, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06744670350841868, |
| "min": 0.06359170853061354, |
| "max": 0.07401181769568546, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9442538491178615, |
| "min": 0.5143249506865436, |
| "max": 1.0505013468962932, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.010303179046656754, |
| "min": 0.00010284552881299412, |
| "max": 0.012369394314046381, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.14424450665319455, |
| "min": 0.0013369918745689236, |
| "max": 0.17563651742966613, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.3477189793642855e-06, |
| "min": 7.3477189793642855e-06, |
| "max": 0.00029523775873027143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010286806571109999, |
| "min": 0.00010286806571109999, |
| "max": 0.003507110630963199, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244920714285714, |
| "min": 0.10244920714285714, |
| "max": 0.19841258571428572, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4342889, |
| "min": 1.3888881, |
| "max": 2.5690368000000006, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002546757935714286, |
| "min": 0.0002546757935714286, |
| "max": 0.009841417312857143, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035654611100000007, |
| "min": 0.0035654611100000007, |
| "max": 0.11692677632000004, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008558954112231731, |
| "min": 0.008558954112231731, |
| "max": 0.23740853369235992, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.11982535570859909, |
| "min": 0.11982535570859909, |
| "max": 1.6618597507476807, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 527.8888888888889, |
| "min": 463.26153846153846, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28506.0, |
| "min": 16510.0, |
| "max": 32679.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.1387073847430724, |
| "min": -1.0000000521540642, |
| "max": 1.3676360400973773, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 61.49019877612591, |
| "min": -32.000001668930054, |
| "max": 84.3025985211134, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.1387073847430724, |
| "min": -1.0000000521540642, |
| "max": 1.3676360400973773, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 61.49019877612591, |
| "min": -32.000001668930054, |
| "max": 84.3025985211134, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.046753494877958914, |
| "min": 0.04361435385932134, |
| "max": 4.421290411668665, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.5246887234097812, |
| "min": 2.5246887234097812, |
| "max": 75.16193699836731, |
| "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": "1774517834", |
| "python_version": "3.10.12 (main, Mar 26 2026, 08:57:09) [GCC 11.4.0]", |
| "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining1 --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1774520951" |
| }, |
| "total": 3116.781296665, |
| "count": 1, |
| "self": 0.7323735379995924, |
| "children": { |
| "run_training.setup": { |
| "total": 0.025316808000752644, |
| "count": 1, |
| "self": 0.025316808000752644 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3116.0236063189996, |
| "count": 1, |
| "self": 2.335334082060399, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.871062339000673, |
| "count": 1, |
| "self": 2.871062339000673 |
| }, |
| "TrainerController.advance": { |
| "total": 3110.7114014069384, |
| "count": 63456, |
| "self": 2.416944356717977, |
| "children": { |
| "env_step": { |
| "total": 2131.2297587630937, |
| "count": 63456, |
| "self": 1893.5081407749494, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 236.2582331820995, |
| "count": 63456, |
| "self": 7.261967437979365, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 228.99626574412014, |
| "count": 62560, |
| "self": 228.99626574412014 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.4633848060448145, |
| "count": 63456, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3106.974517746109, |
| "count": 63456, |
| "is_parallel": true, |
| "self": 1404.4951968869573, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.00233394600036263, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008251440012827516, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015088019990798784, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015088019990798784 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06025734400009242, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006651449994024006, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0006977950006330502, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006977950006330502 |
| }, |
| "communicator.exchange": { |
| "total": 0.05650749300002644, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05650749300002644 |
| }, |
| "steps_from_proto": { |
| "total": 0.0023869110000305227, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004924089998894488, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001894502000141074, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001894502000141074 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1702.4793208591518, |
| "count": 63455, |
| "is_parallel": true, |
| "self": 46.189909491178696, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 36.90663996809417, |
| "count": 63455, |
| "is_parallel": true, |
| "self": 36.90663996809417 |
| }, |
| "communicator.exchange": { |
| "total": 1443.4854034829614, |
| "count": 63455, |
| "is_parallel": true, |
| "self": 1443.4854034829614 |
| }, |
| "steps_from_proto": { |
| "total": 175.89736791691757, |
| "count": 63455, |
| "is_parallel": true, |
| "self": 36.475124435169164, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 139.4222434817484, |
| "count": 507640, |
| "is_parallel": true, |
| "self": 139.4222434817484 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 977.0646982871267, |
| "count": 63456, |
| "self": 4.241087820181747, |
| "children": { |
| "process_trajectory": { |
| "total": 188.6161550889483, |
| "count": 63456, |
| "self": 188.35371648794808, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.26243860100021266, |
| "count": 2, |
| "self": 0.26243860100021266 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 784.2074553779967, |
| "count": 446, |
| "self": 468.06935931197677, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 316.1380960660199, |
| "count": 22827, |
| "self": 316.1380960660199 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.2190002962597646e-06, |
| "count": 1, |
| "self": 1.2190002962597646e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10580727199976536, |
| "count": 1, |
| "self": 0.0012238769995747134, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10458339500019065, |
| "count": 1, |
| "self": 0.10458339500019065 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
