twleung + reinforcementlearning   17

Learning to Compose Skills | himanshusahni.github.io
One of the weaknesses of vanilla deep reinforcement learning is that policies and values learned are typically limited to a single environment, the one the agent was trained on. In other words, it is hard to transfer policies from one setting to another. This is in sharp contrast to how humans learn to do stuff. We draw heavily on past experiences and quickly learn what combination of skills we already have that works well in a new environment.
deeplearning  reinforcementlearning 
february 2018 by twleung
DeepMind’s AI is teaching itself parkour, and the results are adorable - The Verge
Keeping up with the latest AI research can be an odd experience. On the one hand, you’re aware that you’re looking at cutting-edge experimentation, with new papers outlining the ideas and methods...
deeplearning  reinforcementlearning  ai 
july 2017 by twleung
GitHub - Alfredvc/paac: Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning
paac - Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning
deeplearning  reinforcementlearning 
may 2017 by twleung
Value iteration networks | the morning paper
Value Iteration Networks Tamar et al., NIPS 2016 'Value Iteration Networks' won a best paper award at NIPS 2016. It tackles two of the hot issues in reinforcement learning at the moment: incorporating longer range planning into the learned strategies, and improving transfer learning from one problem to another. It's two for the price of…
deeplearning  reinforcementlearning 
march 2017 by twleung

Copy this bookmark:



description:


tags: