dqn

How to implement gradient ascent in a Keras DQN

落爺英雄遲暮 提交于 2021-02-11 12:30:01
问题 Have built a Reinforcement Learning DQN with variable length sequences as inputs, and positive and negative rewards calculated for actions. Some problem with my DQN model in Keras means that although the model runs, average rewards over time decrease, over single and multiple cycles of epsilon. This does not change even after significant period of training. My thinking is that this is due to using MeanSquareError in Keras as the Loss function (minimising error). So I am trying to implement

How to implement gradient ascent in a Keras DQN

生来就可爱ヽ(ⅴ<●) 提交于 2021-02-11 12:27:04
问题 Have built a Reinforcement Learning DQN with variable length sequences as inputs, and positive and negative rewards calculated for actions. Some problem with my DQN model in Keras means that although the model runs, average rewards over time decrease, over single and multiple cycles of epsilon. This does not change even after significant period of training. My thinking is that this is due to using MeanSquareError in Keras as the Loss function (minimising error). So I am trying to implement

Keras CNN for non-image matrix

倾然丶 夕夏残阳落幕 提交于 2020-12-12 10:53:23
问题 I have recently started learning about Deep Learning and Reinforcement Learning, and I am trying to figure out how to code a Convolutional Neural Network using Keras for a matrix of 0s and 1s with 10 rows and 3 columns. The input matrix would look like this for example [ [1, 0, 0], [0, 1, 0], [0, 0, 0], ... ] The output should be another matrix of 0s and 1s, different from the aforementioned input matrix and with a different number of rows and columns. The location of 0s and 1s in the output