def get_qval_sym(self, obs_var, action_var, **kwargs):
qvals = L.get_output(
self._output_layer,
{self._obs_layer: obs_var, self._action_layer: action_var},
**kwargs
)
return TT.reshape(qvals, (-1,))
continuous_mlp_q_function.py 文件源码
python
阅读 21
收藏 0
点赞 0
评论 0
评论列表
文章目录