Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

November 15, 2019 ยท Declared Dead ยท ๐Ÿ› IEEE/RJS International Conference on Intelligent RObots and Systems

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Kevin Sebastian Luck, Mel Vecerik, Simon Stepputtis, Heni Ben Amor, Jonathan Scholz arXiv ID 1911.06833 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.RO, stat.ML Citations 13 Venue IEEE/RJS International Conference on Intelligent RObots and Systems Last Checked 4 months ago
Abstract
Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy Gradient when trained on a latent image embedding. In addition, an extension of DDPG is derived using a value function as critic, making use of a learned deep dynamics model to compute the policy gradient. This approach leads to a symbiotic relationship between the deep reinforcement learning algorithm and the latent trajectory optimizer. The trajectory optimizer benefits from the critic learned by the RL algorithm and the latter from the enhanced exploration generated by the planner. The developed methods are evaluated on two continuous control tasks, one in simulation and one in the real world. In particular, a Baxter robot is trained to perform an insertion task, while only receiving sparse rewards and images as observations from the environment.
Community shame:
Not yet rated
Community Contributions

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

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted