benchmark(davide): Bsuite memory benchmark (#138)
* added r2d2 + a2c configs * changed convergence reward for some env * removed configs that don't converge * removed 'on_policy' param in 2rd2 configs
Showing
想要评论请 注册 或 登录
* added r2d2 + a2c configs * changed convergence reward for some env * removed configs that don't converge * removed 'on_policy' param in 2rd2 configs