泽宇
Followers: 0 Following: 0
Statistics
2 Questions
0 Answers
RANK
234,768
of 295,448
REPUTATION
0
CONTRIBUTIONS
2 Questions
0 Answers
ANSWER ACCEPTANCE
0.0%
VOTES RECEIVED
0
RANK
of 20,227
REPUTATION
N/A
AVERAGE RATING
0.00
CONTRIBUTIONS
0 Files
DOWNLOADS
0
ALL TIME DOWNLOADS
0
RANK
of 153,872
CONTRIBUTIONS
0 Problems
0 Solutions
SCORE
0
NUMBER OF BADGES
0
CONTRIBUTIONS
0 Posts
CONTRIBUTIONS
0 Public Channels
AVERAGE RATING
CONTRIBUTIONS
0 Highlights
AVERAGE NO. OF LIKES
Feeds
Question
When using the reinforcement learning toolbox, when training the agent, there will be a problem that action is the boundary.
我在用深matlab强化学习工具箱进行自定义环境智能体训练,在第一次训练时(未得到奖励时),智能体给出的action是action约束范围内的值,然而在第二次训练时(得到第一次训练的奖励后),智能体给出的action是action却是约束范围的边界值?并且...
7 months ago | 1 answer | 0
1
answerQuestion
TD3算法训练时动作总是输出边界值
我在使用TD3算法训练完成后,无论训练过程中奖励曲线是否收敛,动作总是输出边界值或者输出完全不正确。我的state的值在0-20000,动作边界在0-15000.是哪里出了问题,是自定义环境创建的不正确还是哪里?需要对输入输出进行归一化吗
9 months ago | 1 answer | 0