pytorch/examples

Actor critic example not using discount rate properly

Open

#744 创建于 2020年3月27日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Python (21,634 star) (9,429 fork)batch import
good first issuetriaged

描述

The Actor Critic example (which is actually an implementation of REINFORCE-with-baseline as pointed out in https://github.com/pytorch/examples/issues/573), does not use the discount rate properly.

The loss should include \gamma ^ t, as shown in the box on page 330 of Sutton & Barto:

image

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-3 hours
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
REINFORCE algorithmPyTorch basicsDiscount factor concept
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
45
研究方向
Examine the actor critic example file (likely in the reinforcement learning folder). The current code likely computes the loss without weighting by gamma^t. Refer to the referenced issue #573 and the Sutton & Barto equation. The fix involves multiplying each log probability term by gamma^t in the policy gradient loss calculation. Check the comments in the issue for any additional guidance.
Actor critic example not using discount rate properly · pytorch/examples#744 | Good First Issue