issues
search
HumanCompatibleAI
/
adversarial-policies
Find best-response to a fixed policy in multi-agent RL
MIT License
275
stars
47
forks
source link
Policy serializing
#38
Open
AdamGleave
opened
4 years ago
AdamGleave
commented
4 years ago
[ ] Use new format for VecNormalize:
https://github.com/hill-a/stable-baselines/pull/525
[ ] Switch to context manager to ensure policies are closed?
[ ] Consider switching to
BasePolicy
rather than
BaseRLModel
?
BasePolicy
rather thanBaseRLModel
?