Search Results for author:
Found 3 papers, 2 papers with code
Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
Given a weak base-policy trained by offline imitation of demonstrations, FISH computes rewards that correspond to the "match" between the robot's behavior and the demonstrations.
Watch and Match: Supercharging Imitation with Regularized Optimal Transport
Our experiments on 20 visual control tasks across the DeepMind Control Suite, the OpenAI Robotics Suite, and the Meta-World Benchmark demonstrate an average of 7. 8X faster imitation to reach 90% of expert performance compared to prior state-of-the-art methods.
Lightweight Modules for Efficient Deep Learning based Image Restoration
We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
