Changing how DQN agent explores

2 次查看（过去 30 天）

Michael 2021-7-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/877048-changing-how-dqn-agent-explores

评论： Michael 2021-7-13

Hi,

I'm using a DQN agent with epsilon-greedy exploration. The problem is that my agent sees state 1 99% of the time, so it never learns to act in other states. By the time it learns to get to state 2 from state 1, epsilon has already decayed significantly and the agent gets stuck taking a sub-optimal action in state 2. Is there a way to implement some other form of exploration, like using a Boltzmann distribution? Thanks for your time.

2 个评论
显示无隐藏无

Tanay Gupta 2021-7-13

Can you give a brief description of the states and the respective transitions?

Michael 2021-7-13

Sure, thanks for the reply! My agent is observing the noise present in two waveforms and whether two boxes are on/off. Turning a box off gets rid of the noise in its associated waveform (actions are turn off box 1, turn off box 2, turn off both). The first state is the state where both boxes are on and the waveforms have the lowest level of noise. In this state, I want the action to be "do nothing." Unfortunately, my agent has to take a lot of steps each episode to reduce detection time of the noise. This means that my agent almost always turns off the boxes before it sees a high level of noise a few seconds into the simulation (it has to take approximately 100 "do nothing" actions before seeing the high level of noise. So a different way of exploring/possibly a different RL agent is needed.

请先登录，再进行评论。

请先登录，再回答此问题。