Check that the code implementation is accurate and reasonable

[StepNeverStop]

• [x] check and fix C51 [deaab73]
• [x] check qrdqn [deaab73]
• [ ] check iqn
• [ ] check and fix Rainbow
• [ ] check on-policy buffer sampling
• [ ] check function discounted_sum
• [ ] check function calculate_td_error
• [ ] checke whether works well when training with visual input
• [ ] fix TRPO that step_size sometime be nan
• [ ] check vdn and qmix

[StepNeverStop]

• [x] 检查将代码中关于运算维度的选择(dim/axis)把能设置为-1的都设置为-1。

[StepNeverStop]

• [x] 校正RNN隐状态在使用探索策略时的迭代更新 abf6b0a
• [x] 实现按策略与环境交互的间隔更新策略 abf6b0a