Commit Graph

63 Commits

Author SHA1 Message Date
weixin_46229132
27829c5d48 修改场景 2025-03-31 14:23:29 +08:00
weixin_46229132
dab8f4fd8f 调整奖励函数 2025-03-31 11:12:01 +08:00
weixin_46229132
84f69f4293 离散情况 2025-03-29 21:28:39 +08:00
weixin_46229132
3e6887c655 每一个加一个奖励 2025-03-29 16:53:03 +08:00
weixin_46229132
f347ca8276 微调分区 2025-03-29 16:28:30 +08:00
along
f05f8400fb ddpg求解env_part 2025-03-29 12:00:26 +08:00
along
0cf336c96d ppo内层加入ga 2025-03-29 11:43:04 +08:00
weixin_46229132
ff2b914eb5 修复env_partion bug 2025-03-29 10:48:47 +08:00
weixin_46229132
2c88915112 跑通PPO partition 2025-03-28 21:37:31 +08:00
weixin_46229132
8d79e8cc66 mTSP代码 2025-03-28 19:57:44 +08:00
weixin_46229132
656e822528 format 2025-03-28 15:13:23 +08:00
weixin_46229132
a375832b6c 添加q-learning TSP 2025-03-28 10:53:41 +08:00
weixin_46229132
1485fb2bd6 更新q_table 2025-03-27 21:48:07 +08:00
weixin_46229132
6f8fcd15b7 加入q learning 2025-03-27 20:50:46 +08:00
weixin_46229132
6f44d142bc 修改模拟退火bug 2025-03-24 19:28:24 +08:00
weixin_46229132
fe37f7ac0f 修改超参数设置 2025-03-24 17:09:51 +08:00
weixin_46229132
61be8ad37c 修改蒙特卡洛的输出 2025-03-24 16:11:38 +08:00
weixin_46229132
9599215e2e 模拟退火微调分割 2025-03-24 15:42:42 +08:00
weixin_46229132
d9d1214f7c 小改 2025-03-22 21:44:06 +08:00
weixin_46229132
8e8d9a25df 修改GA bug 2025-03-22 21:43:11 +08:00
weixin_46229132
17acfa5409 修改GA bug 2025-03-22 17:24:45 +08:00
weixin_46229132
c9db9244b3 添加遍历-遗传算法求解 2025-03-22 17:16:58 +08:00
weixin_46229132
a9ee5ceec7 环境增加delay_time 2025-03-22 09:47:52 +08:00
weixin_46229132
5b468deb9d SAC 2025-03-21 16:04:42 +08:00
weixin_46229132
67c7a9d6c7 DQN让它先看答案 2025-03-20 14:05:15 +08:00
weixin_46229132
f4fb963c06 修改env参数 2025-03-20 09:29:30 +08:00
weixin_46229132
c5023fb360 添加价值评估的mask 2025-03-19 21:52:33 +08:00
weixin_46229132
3dba6e4a53 修改离散环境,连续不动给惩罚 2025-03-19 20:58:34 +08:00
weixin_46229132
4972306ca7 更新env_dis 2025-03-19 20:40:35 +08:00
weixin_46229132
ff23b5e745 调整奖励 2025-03-19 16:31:23 +08:00
weixin_46229132
d364a1e4df 修ppo bug 2025-03-19 15:23:55 +08:00
weixin_46229132
6dc285d3f8 加入PPO代码 2025-03-19 15:12:52 +08:00
weixin_46229132
7ca5ce08b1 修改环境 2025-03-19 14:22:24 +08:00
weixin_46229132
e35dd10326 验证阶段加输出,更新奖励 2025-03-19 11:29:02 +08:00
weixin_46229132
c96c36d4cd 调整eval的输出 2025-03-19 10:58:43 +08:00
weixin_46229132
2362de4c54 修改dqn 2025-03-19 01:04:03 +08:00
weixin_46229132
f19e8fbdbf 加入dqn算法 2025-03-18 21:16:48 +08:00
weixin_46229132
343008bc9f 简化初始化迷宫的方式 2025-03-18 17:27:49 +08:00
weixin_46229132
55e45fe14e 小改ddpg main 2025-03-18 14:45:50 +08:00
weixin_46229132
b3812a3193 format ddpg_main 2025-03-18 14:30:41 +08:00
weixin_46229132
19f8b6246a test 2025-03-18 14:29:16 +08:00
weixin_46229132
75e5237272 修改DDPG 2025-03-14 16:06:59 +08:00
weixin_46229132
ab51727253 添加ddpg代码 2025-03-14 15:27:05 +08:00
weixin_46229132
4fdb8aa152 env代码小调整 2025-03-14 11:17:12 +08:00
weixin_46229132
dfec68e122 修改蒙特卡洛采样法 2025-03-14 11:01:02 +08:00
weixin_46229132
b3b5e597b8 添加requirements.txt 2025-03-14 10:10:09 +08:00
weixin_46229132
c1eb9d9528 就用cpu训练网络 2025-03-14 09:45:46 +08:00
weixin_46229132
64935bf92f 添加人工操作,修改环境bug 2025-03-14 09:42:56 +08:00
weixin_46229132
db890f83cf 改网络的激活函数 2025-03-14 09:22:40 +08:00
weixin_46229132
3086413171 修改car_pos 2025-03-13 21:28:30 +08:00