Closed satpreetsingh closed 5 months ago
I trained some agents using IPPO on MPE with the benchmark code, and used the following code for inference and animation generation: https://github.com/FLAIROx/JaxMARL/pull/72#
$ python ippo_rnn_mpe.py {'returns': -102.80365, 'env_step': 0} {'returns': -100.726265, 'env_step': 3072} {'returns': -104.75728, 'env_step': 6144} {'returns': -94.75876, 'env_step': 9216} {'returns': -89.8966, 'env_step': 12288} {'returns': -94.21084, 'env_step': 15360} {'returns': -92.89967, 'env_step': 18432} {'returns': -93.211845, 'env_step': 21504} ... {'returns': -67.70681, 'env_step': 1978368} {'returns': -68.14425, 'env_step': 1981440} {'returns': -68.150986, 'env_step': 1984512} {'returns': -66.487785, 'env_step': 1987584} {'returns': -65.92587, 'env_step': 1990656} {'returns': -67.4093, 'env_step': 1993728} {'returns': -66.18083, 'env_step': 1996800} Saved: ippo_mpe_ep00.gif Saved: ippo_mpe_ep01.gif
Seems like the training process converges, but visualizing the trained agents reveals poor policies. Animations attached.
@amacrutherford Requesting an update on this issue. Thanks!
Hi! please see PR #77
I trained some agents using IPPO on MPE with the benchmark code, and used the following code for inference and animation generation: https://github.com/FLAIROx/JaxMARL/pull/72#
Seems like the training process converges, but visualizing the trained agents reveals poor policies. Animations attached.
![ippo_mpe_ep00](https://github.com/FLAIROx/JaxMARL/assets/931141/08e7b834-ce8a-4565-a567-b38837843cd6)