Loading video...
Video Failed to Load
Congratulations also to Patrick ๐ for his #ICLR paper on Temporal Difference (TD) learning , in it We solve the decades-old puzzle of why TD can solve complex RL tasks that Gradient Descent cannot.
22,074 views โข 1 year ago โขvia X (Twitter)
0 Comments
No comments available
Comments from the original post will appear here
![Robots struggle with strict action rulesโฆmemory and symbols help them learn fast. [Project + Full video link โฌ๏ธ] Robots struggle when tasks require specific steps in a fixed order. What if memory helped them think symbolically and learn faster? Solving tasks like unlocking a door then opening it is hard for deep RL. But by learning constraint relationships and storing them in memory, robots can solve these tasks much faster; with fewer trials and less training. Why it works โ
Learns symbolic rules about action constraints โ
Uses memory to transfer what it learned across tasks โ
Handles real-world exploration with just 30 minutes of data โ
Needs 10x fewer episodes than deep RL approaches This memory-based method shows a promising path forward for robots learning structured, real-world tasks. Full video: Paper: Thank you, Mrinal Verghese for sharing this amazing work! ๐](https://image.24vids.com/tw-1910952836730433725/amplify_video_thumb/1910952827377111040/img/O_xQuJtbdzWr7FUV.jpg)
