Dynamic Path Planning of Unknown Environment Based on Deep Reinforcement Learning
Pygame module in PYTHON is used to establish dynamic environments. 以激光雷達信號和局部目標位置爲輸入，利用卷積神經網絡(CNNs)對環境狀態進行泛化,而Q-learning增強了環境中動態避障和智能體局部規劃的能力.結果表明，經過不同動態環境的訓練和新環境的測試，該agent能夠在未知的動態環境中成功地到達局部目標位置。 之前的工
相關文章
- 1. A Novel GRU-RNN Network Model for Dynamic Path Planning of Mobile Robot
- 2. [Reinforcement Learning] 動態規劃(Planning)
- 3. A Survey of Recommender Systems Based on Deep Learning （1）
- 4. Summary of defect detection algorithms based on deep learning
- 5. PR10.10:#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- 6. Deep Reinforcement Learning
- 7. Reinforcement learning: integrating learning and planning, exploitation and exploration
- 8. Reinforcement Learning: Planning by DP
- 9. Planning by Dynamic Programming
- 10. Reinforcement Learning（二）：Value-Based
- 更多相關文章...
- • SVG
- SVG 教程 - • ASP Path 屬性 - ASP 教程
- • Java Agent入門實戰（三）-JVM Attach原理與使用
- • JDK13 GA發佈：5大特性解讀
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. A Novel GRU-RNN Network Model for Dynamic Path Planning of Mobile Robot
- 2. [Reinforcement Learning] 動態規劃(Planning)
- 3. A Survey of Recommender Systems Based on Deep Learning （1）
- 4. Summary of defect detection algorithms based on deep learning
- 5. PR10.10:#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- 6. Deep Reinforcement Learning
- 7. Reinforcement learning: integrating learning and planning, exploitation and exploration
- 8. Reinforcement Learning: Planning by DP
- 9. Planning by Dynamic Programming
- 10. Reinforcement Learning（二）：Value-Based