更新算法模版

projects/codes/QLearning/config/CliffWalking-v0_QLearning_Test.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: CliffWalking-v0
+  mode: test
+  load_checkpoint: true
+  load_path: Train_CliffWalking-v0_QLearning_20221030-013856
+  max_steps: 200
+  save_fig: true
+  seed: 1
+  show_fig: false
+  test_eps: 20
+  train_eps: 400
+algo_cfg:
+  epsilon_decay: 300
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.95
+  lr: 0.1

projects/codes/QLearning/config/CliffWalking-v0_QLearning_Train.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: CliffWalking-v0
+  mode: train
+  load_checkpoint: false
+  load_path: Train_CartPole-v1_DQN_20221026-054757
+  max_steps: 200
+  save_fig: true
+  seed: 1
+  show_fig: false
+  test_eps: 20
+  train_eps: 800
+algo_cfg:
+  epsilon_decay: 300
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.95
+  lr: 0.1

projects/codes/QLearning/config/FrozenLakeNoSlippery-v1_QLearning_Test.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: FrozenLakeNoSlippery-v1
+  mode: test
+  load_checkpoint: true
+  load_path: Train_FrozenLakeNoSlippery-v1_QLearning_20221030-014504
+  max_steps: 200
+  save_fig: true
+  seed: 10
+  show_fig: false
+  test_eps: 20
+  train_eps: 800
+algo_cfg:
+  epsilon_decay: 2000
+  epsilon_end: 0.1
+  epsilon_start: 0.7
+  gamma: 0.95
+  lr: 0.9

projects/codes/QLearning/config/FrozenLakeNoSlippery-v1_QLearning_Train.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: FrozenLakeNoSlippery-v1
+  mode: train
+  load_checkpoint: false
+  load_path: Train_CartPole-v1_DQN_20221026-054757
+  max_steps: 200
+  save_fig: true
+  seed: 10
+  show_fig: false
+  test_eps: 20
+  train_eps: 800
+algo_cfg:
+  epsilon_decay: 2000
+  epsilon_end: 0.1
+  epsilon_start: 0.7
+  gamma: 0.95
+  lr: 0.9

projects/codes/QLearning/config/Racetrack-v0_QLearning_Test.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: Racetrack-v0
+  mode: test
+  load_checkpoint: true
+  load_path: Train_Racetrack-v0_QLearning_20221030-014833
+  max_steps: 200
+  save_fig: true
+  seed: 10
+  show_fig: false
+  test_eps: 20
+  train_eps: 400
+algo_cfg:
+  epsilon_decay: 300
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.9
+  lr: 0.1

projects/codes/QLearning/config/Racetrack-v0_QLearning_Train.yaml

@@ -0,0 +1,19 @@
+general_cfg:
+  algo_name: QLearning
+  device: cpu
+  env_name: Racetrack-v0
+  mode: train
+  load_checkpoint: false
+  load_path: Train_CartPole-v1_DQN_20221026-054757
+  max_steps: 200
+  save_fig: true
+  seed: 10
+  show_fig: false
+  test_eps: 20
+  train_eps: 400
+algo_cfg:
+  epsilon_decay: 300
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.9
+  lr: 0.1

projects/codes/QLearning/config/config.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python
+# coding=utf-8
+'''
+Author: JiangJi
+Email: johnjim0816@gmail.com
+Date: 2022-10-30 01:23:07
+LastEditor: JiangJi
+LastEditTime: 2022-10-30 01:39:54
+Discription: default parameters of QLearning
+'''
+from common.config import GeneralConfig,AlgoConfig
+
+class GeneralConfigQLearning(GeneralConfig):
+    def __init__(self) -> None:
+        self.env_name = "CliffWalking-v0" # name of environment
+        self.algo_name = "QLearning" # name of algorithm
+        self.mode = "train" # train or test
+        self.seed = 1 # random seed
+        self.device = "cpu" # device to use
+        self.train_eps = 400 # number of episodes for training
+        self.test_eps = 20 # 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 AlgoConfigQLearning(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 = 300 # epsilon decay rate
+        self.gamma = 0.90 # discount factor
+        self.lr = 0.1 # learning rate