|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.287369042634964, |
|
"min": 0.2667141854763031, |
|
"max": 1.4335803985595703, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8565.896484375, |
|
"min": 8129.4482421875, |
|
"max": 43489.09375, |
|
"count": 36 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 1079961.0, |
|
"min": 29952.0, |
|
"max": 1079961.0, |
|
"count": 36 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 1079961.0, |
|
"min": 29952.0, |
|
"max": 1079961.0, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5470317602157593, |
|
"min": -0.0999130979180336, |
|
"max": 0.6519434452056885, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 147.69857788085938, |
|
"min": -24.079055786132812, |
|
"max": 179.93638610839844, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.006864666938781738, |
|
"min": -0.004418520722538233, |
|
"max": 0.4534786641597748, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.8534600734710693, |
|
"min": -1.2195117473602295, |
|
"max": 107.47444152832031, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07089045304850775, |
|
"min": 0.06409058919803427, |
|
"max": 0.0721138468342057, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9924663426791085, |
|
"min": 0.48811832188388415, |
|
"max": 1.0817077025130855, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015651139642050976, |
|
"min": 0.000885894968271914, |
|
"max": 0.015983723027490442, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21911595498871367, |
|
"min": 0.011516634587534881, |
|
"max": 0.23051815697616287, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 9.528876044519475e-06, |
|
"min": 9.528876044519475e-06, |
|
"max": 0.00029559148198898697, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00013340426462327265, |
|
"min": 0.00013340426462327265, |
|
"max": 0.0035707995733699088, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10317625974025976, |
|
"min": 0.10317625974025976, |
|
"max": 0.19853049350649352, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4444676363636366, |
|
"min": 1.3897134545454546, |
|
"max": 2.590266454545455, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00032730834805194794, |
|
"min": 0.00032730834805194794, |
|
"max": 0.009853196301298703, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.004582316872727271, |
|
"min": 0.004582316872727271, |
|
"max": 0.11904761880909089, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.009886262938380241, |
|
"min": 0.009681078605353832, |
|
"max": 0.4267338216304779, |
|
"count": 36 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.13840767741203308, |
|
"min": 0.1355351060628891, |
|
"max": 2.9871368408203125, |
|
"count": 36 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 361.26190476190476, |
|
"min": 301.77777777777777, |
|
"max": 999.0, |
|
"count": 36 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30346.0, |
|
"min": 15984.0, |
|
"max": 32568.0, |
|
"count": 36 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.519659504649185, |
|
"min": -1.0000000521540642, |
|
"max": 1.6982222048772706, |
|
"count": 36 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 127.65139839053154, |
|
"min": -30.415201626718044, |
|
"max": 155.36799799650908, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.519659504649185, |
|
"min": -1.0000000521540642, |
|
"max": 1.6982222048772706, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 127.65139839053154, |
|
"min": -30.415201626718044, |
|
"max": 155.36799799650908, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03621241321005592, |
|
"min": 0.03196428829461284, |
|
"max": 8.495654990896583, |
|
"count": 36 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.0418427096446976, |
|
"min": 2.8650760277814697, |
|
"max": 135.93047985434532, |
|
"count": 36 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 36 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 36 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1727776843", |
|
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.1.0.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": "1727780588" |
|
}, |
|
"total": 3744.8172190179994, |
|
"count": 1, |
|
"self": 0.6511105679992397, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07290274000001773, |
|
"count": 1, |
|
"self": 0.07290274000001773 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3744.09320571, |
|
"count": 1, |
|
"self": 2.5731807299316642, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.523525099000153, |
|
"count": 1, |
|
"self": 2.523525099000153 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3738.9151695030687, |
|
"count": 70468, |
|
"self": 2.9955448220648577, |
|
"children": { |
|
"env_step": { |
|
"total": 2475.3934913830053, |
|
"count": 70468, |
|
"self": 2290.3742062289784, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 183.44057437001788, |
|
"count": 70468, |
|
"self": 7.992111577047808, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 175.44846279297008, |
|
"count": 68808, |
|
"self": 175.44846279297008 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.5787107840089902, |
|
"count": 70468, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3736.3162278599502, |
|
"count": 70468, |
|
"is_parallel": true, |
|
"self": 1655.792529376963, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0033808529999532766, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0011859959997764236, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002194857000176853, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002194857000176853 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06702927700007422, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008099440001387848, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000549130999843328, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000549130999843328 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06341267700008757, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06341267700008757 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0022575250000045344, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004763680003634363, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001781156999641098, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001781156999641098 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2080.523698482987, |
|
"count": 70467, |
|
"is_parallel": true, |
|
"self": 56.09306456202694, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 34.77281887001436, |
|
"count": 70467, |
|
"is_parallel": true, |
|
"self": 34.77281887001436 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1844.6171182019805, |
|
"count": 70467, |
|
"is_parallel": true, |
|
"self": 1844.6171182019805 |
|
}, |
|
"steps_from_proto": { |
|
"total": 145.04069684896535, |
|
"count": 70467, |
|
"is_parallel": true, |
|
"self": 31.630093902177123, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 113.41060294678823, |
|
"count": 563736, |
|
"is_parallel": true, |
|
"self": 113.41060294678823 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1260.5261332979985, |
|
"count": 70468, |
|
"self": 5.006909977063287, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 193.3450703299311, |
|
"count": 70468, |
|
"self": 193.11726744693055, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.22780288300054963, |
|
"count": 2, |
|
"self": 0.22780288300054963 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1062.1741529910041, |
|
"count": 498, |
|
"self": 421.50339530400197, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 640.6707576870022, |
|
"count": 25095, |
|
"self": 640.6707576870022 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.184000211651437e-06, |
|
"count": 1, |
|
"self": 1.184000211651437e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08132919399940874, |
|
"count": 1, |
|
"self": 0.0019687249996422906, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.07936046899976645, |
|
"count": 1, |
|
"self": 0.07936046899976645 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |