Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models

November 02, 2020 Β· Declared Dead Β· πŸ› IEEE International Conference on Robotics and Automation

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yuchen Wu, Melissa Mozifian, Florian Shkurti arXiv ID 2011.01298 Category cs.RO: Robotics Cross-listed cs.LG Citations 25 Venue IEEE International Conference on Robotics and Automation Last Checked 4 months ago
Abstract
The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To address these drawbacks we propose a method that combines reinforcement and imitation learning by shaping the reward function with a state-and-action-dependent potential that is trained from demonstration data, using a generative model. We show that this accelerates policy learning by specifying high-value areas of the state and action space that are worth exploring first. Unlike the majority of existing methods that assume optimal demonstrations and incorporate the demonstration data as hard constraints on policy optimization, we instead incorporate demonstration data as advice in the form of a reward shaping potential trained as a generative model of states and actions. In particular, we examine both normalizing flows and Generative Adversarial Networks to represent these potentials. We show that, unlike many existing approaches that incorporate demonstrations as hard constraints, our approach is unbiased even in the case of suboptimal and noisy demonstrations. We present an extensive range of simulations, as well as experiments on the Franka Emika 7DOF arm, to demonstrate the practicality of our method.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Robotics

Died the same way β€” πŸ‘» Ghosted