Hello, I trained a TD3 agent using the RL Toolbox and the agent is giving a better reward than the untrained agent. But the trained agent is giving the same actions and the same reward for 10 simulations (I used the "Simulate" option of the Toolbox). Is this behaviour normal for an RL agent ?

Thank you in advance.Hello, I trained a TD3 agent using the RL Toolbox and the agent is giving a better reward than the untrained agent. But the trained agent is giving the same actions and the same reward for 10 simulations (I used the "Simulate" option of the Toolbox). Is this behaviour normal for an RL agent ?

Thank you in advance. Hello, I trained a TD3 agent using the RL Toolbox and the agent is giving a better reward than the untrained agent. But the trained agent is giving the same actions and the same reward for 10 simulations (I used the "Simulate" option of the Toolbox). Is this behaviour normal for an RL agent ?

Thank you in advance. rl, machine learning, simulation, matlab, ai MATLAB Answers — New Questions

​