When running the iddpg algorithm in the MAMujoco environment, the memory keeps increasing.

[whbeats]

Hello! When running the iddpg algorithm in the MAMujoco environment, the memory keeps increasing. Finally, when the memory is full, an error will be reported and stopped. But when I run the mappo algorithm, the memory does not increase significantly.
thank you very much

Current time: 2024-09-21 22:49:39 (running for 00:00:42.09)
Memory usage on this node: 8.6/31.2 GiB
Using FIFO scheduling algorithm.
Resources requested: 2.0/20 CPUs, 1.0/1 GPUs, 0.0/13.19 GiB heap, 0.0/10.0 GiB objects (0.0/1.0 accelerator_type:G)
Result logdir: /home/wang/Codes/MyCodes/010_MAMJC/MARLlib/exp_results/iddpg_mlp_2AgentHalfCheetah
Number of trials: 1/1 (1 RUNNING)
...
Memory usage on this node: 10.6/31.2 GiB
...
Memory usage on this node: 10.8/31.2 GiB
...
Memory usage on this node: 16.0/31.2 GiB

[whbeats]

In addition, after I run the code, the following prompt appears. Is it related to the memory gradually filling up?

[HyperEdge({bfoot, bshin}), HyperEdge({bshin, bthigh}), HyperEdge({bthigh, fthigh}), HyperEdge({fshin, fthigh}), HyperEdge({fshin, ffoot})]
[HyperEdge({bfoot, bshin}), HyperEdge({bshin, bthigh}), HyperEdge({bthigh, fthigh}), HyperEdge({fshin, fthigh}), HyperEdge({fshin, ffoot})]
/home/wang/.conda/envs/MAMJC/lib/python3.8/site-packages/gym/logger.py:34: UserWarning: WARN: Box bound precision lowered by casting to float32
warnings.warn(colorize("%s: %s" % ("WARN", msg % args), "yellow"))
2024-09-21 22:48:57,669 INFO logger.py:605 -- pip install 'ray[tune]' to see TensorBoard files.
2024-09-21 22:48:57,669 WARNING callback.py:114 -- The TensorboardX logger cannot be instantiated because either TensorboardX or one of it's dependencies is not installed. Please make sure you have the latest version of TensorboardX installed: pip install -U tensorboardx
2024-09-21 22:48:57,784 WARNING worker.py:496 -- ray.get_gpu_ids() will always return the empty list when called from the driver. This is because Ray does not manage GPU allocations to the driver process.
:task_name:bundle_reservation_check_func
:actor_name:IDDPGTrainer
2024-09-21 22:48:57,832 WARNING deprecation.py:38 -- DeprecationWarning: simple_optimizer has been deprecated. This will raise an error in the future!
2024-09-21 22:48:57,832 INFO trainer.py:770 -- Current log_level is WARN. For more information, set 'log_level': 'INFO' / 'DEBUG' or use the -v and -vv flags.
:actor_name:RolloutWorker
[HyperEdge({bshin, bfoot}), HyperEdge({bshin, bthigh}), HyperEdge({fthigh, bthigh}), HyperEdge({fthigh, fshin}), HyperEdge({ffoot, fshin})]
[HyperEdge({bshin, bfoot}), HyperEdge({bshin, bthigh}), HyperEdge({fthigh, bthigh}), HyperEdge({fthigh, fshin}), HyperEdge({ffoot, fshin})]
2024-09-21 22:48:57,895 WARNING deprecation.py:38 -- DeprecationWarning: SampleBatch['is_training'] has been deprecated. Use SampleBatch.is_training instead. This will raise an error in the future!
2024-09-21 22:48:57,899 WARNING rollout_worker.py:578 -- You are running ray with local_mode=True, but have configured 1 GPUs to be used! In local mode, Policies are placed on the CPU and the num_gpus setting is ignored.
/home/wang/.conda/envs/MAMJC/lib/python3.8/site-packages/ray/rllib/agents/ddpg/ddpg_torch_model.py:103: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /pytorch/torch/csrc/utils/tensor_numpy.cpp:180.)
torch.from_numpy(self.action_space.low).float())
2024-09-21 22:48:57,908 WARNING deprecation.py:38 -- DeprecationWarning: simple_optimizer has been deprecated. This will raise an error in the future!
/home/wang/.conda/envs/MAMJC/lib/python3.8/site-packages/gym/logger.py:34: UserWarning: WARN: Box bound precision lowered by casting to float32
warnings.warn(colorize("%s: %s" % ("WARN", msg % args), "yellow"))
2024-09-21 22:48:57,914 WARNING rollout_worker.py:578 -- You are running ray with local_mode=True, but have configured 1 GPUs to be used! In local mode, Policies are placed on the CPU and the num_gpus setting is ignored.
2024-09-21 22:48:57,920 WARNING util.py:57 -- Install gputil for GPU system monitoring.
[HyperEdge({bfoot, bshin}), HyperEdge({bshin, bthigh}), HyperEdge({fthigh, bthigh}), HyperEdge({fthigh, fshin}), HyperEdge({ffoot, fshin})]
[HyperEdge({bfoot, bshin}), HyperEdge({bshin, bthigh}), HyperEdge({fthigh, bthigh}), HyperEdge({fthigh, fshin}), HyperEdge({ffoot, fshin})]
:actor_name:IDDPGTrainer