Sign Up to like & get
recommendations!
2
Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3278208
Abstract: Training image-based reinforcement learning (RL) agents are sample-inefficient, limiting their effectiveness in real-world manipulation tasks. Sim2Real, which involves training in simulations and transferring to the real world, effectively reduces the dependence on real data. However,…
read more here.
Keywords:
reinforcement learning;
seg curl;
curl;
contrastive unsupervised ... See more keywords