Sign up to save your podcasts
Or
Share RoboMeter: Learning Dense Rewards from Successes and Failures
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
RoboMeter: Learning Dense Rewards from Successes and Failures
RoboMeter trains dense reward models from both successful and failed robot trajectories, solving a key gap in prior methods that only learn from expert demos.
View all episodes
By Shaoqing TanRoboMeter trains dense reward models from both successful and failed robot trajectories, solving a key gap in prior methods that only learn from expert demos.