Reinforcement-learning-with-tensorflow Questions about the 5.2_Prioritized_Replay

Questions about the 5.2_Prioritized_Replay_DQN

Open seey0u opened this issue 5 years ago • 0 comments

Thanks for you code, but I just change the code at the 69 line with 'his_prio = train(RL_natural)'. The meaning is I train the same object twice, but the result is the same with the original code, or I exchange the original code's 68 line and the 69 line, I get the opposite conclusion from the original code. Does anyone have the same problem as me?

Nov 25 '19 08:11 seey0u

Reinforcement-learning-with-tensorflow Reinforcement-learning-with-tensorflow copied to clipboard

Questions about the 5.2_Prioritized_Replay_DQN

Reinforcement-learning-with-tensorflow
Reinforcement-learning-with-tensorflow copied to clipboard