# Why would the agent always take the same action in the test environment?

I'm trying to set up an agent with PPO2. But I've tried with:

• A2C
• DQN
• PPO2

However, in the test environment, the agent always takes the same action, and the total profit is negative.

What can be the problem?

My colab code

• Hello. Welcome to AI SE. Please, take the time to edit your post to 1. describe (at least briefly) the problem you're trying to solve with RL, 2. report the hyper-parameters that you're using (e.g. the number of training time steps you use to train the agent before you test the agent), etc.
– nbro
Sep 18 at 13:51