更新PPO，增加PER DQN

projects/codes/PER_DQN/config/CartPole-v1_PER_DQN_Test.yaml

@@ -0,0 +1,22 @@
+general_cfg:
+  algo_name: PER_DQN
+  device: cpu
+  env_name: CartPole-v1
+  mode: test
+  load_checkpoint: true
+  load_path: Train_CartPole-v1_PER_DQN_20221113-162804
+  max_steps: 200
+  save_fig: true
+  seed: 0
+  show_fig: false
+  test_eps: 10
+  train_eps: 200
+algo_cfg:
+  batch_size: 64
+  buffer_size: 100000
+  epsilon_decay: 500
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.95
+  lr: 0.0001
+  target_update: 4

projects/codes/PER_DQN/config/CartPole-v1_PER_DQN_Train.yaml

@@ -0,0 +1,22 @@
+general_cfg:
+  algo_name: PER_DQN
+  device: cuda
+  env_name: CartPole-v1
+  mode: train
+  load_checkpoint: false
+  load_path: Train_CartPole-v1_PER_DQN_20221026-054757
+  max_steps: 200
+  save_fig: true
+  seed: 0
+  show_fig: false
+  test_eps: 10
+  train_eps: 200
+algo_cfg:
+  batch_size: 64
+  buffer_size: 100000
+  epsilon_decay: 500
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.95
+  lr: 0.0001
+  target_update: 4

projects/codes/PER_DQN/config/config.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: JiangJi
+Email: johnjim0816@gmail.com
+Date: 2022-10-30 00:37:33
+LastEditor: JiangJi
+LastEditTime: 2022-10-30 01:19:08
+Discription: default parameters of DQN
+'''
+from common.config import GeneralConfig,AlgoConfig
+class GeneralConfigDQN(GeneralConfig):
+    def __init__(self) -> None:
+        self.env_name = "CartPole-v1" # name of environment
+        self.algo_name = "PER_DQN" # name of algorithm
+        self.mode = "train" # train or test
+        self.seed = 1 # random seed
+        self.device = "cuda" # device to use
+        self.train_eps = 200 # number of episodes for training
+        self.test_eps = 10 # number of episodes for testing
+        self.max_steps = 200 # max steps for each episode
+        self.load_checkpoint = False
+        self.load_path = "tasks" # path to load model
+        self.show_fig = False # show figure or not
+        self.save_fig = True # save figure or not
+        
+class AlgoConfigDQN(AlgoConfig):
+    def __init__(self) -> None:
+        # set epsilon_start=epsilon_end can obtain fixed epsilon=epsilon_end
+        self.epsilon_start = 0.95 # epsilon start value
+        self.epsilon_end = 0.01 # epsilon end value
+        self.epsilon_decay = 500 # epsilon decay rate
+        self.hidden_dim = 256 # hidden_dim for MLP
+        self.gamma = 0.95 # discount factor
+        self.lr = 0.0001 # learning rate
+        self.buffer_size = 100000 # size of replay buffer
+        self.batch_size = 64 # batch size
+        self.target_update = 4 # target network update frequency