English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In complex environments with high dimension, training a reinforcementlearning (RL) model from scratch often suffers from lengthy and tediouscollection of agent-environment interactions. Instead, leveraging expertdemonstration to guide RL agent can boost sample efficiency and improve finalconvergence. In order to better integrate expert prior with on-policy RLmodels, we propose a generic framework for Learning from Demonstration (LfD)based on actor-critic algorithms. Technically, we first employ K-Meansclustering to evaluate the similarity of sampled exploration with demonstrationdata. Then we increase the likelihood of actions in similar frames by modifyingthe gradient update strategy to leverage demonstration. We conduct experimentson 4 standard benchmark environments in Mujoco and 2 self-designed roboticenvironments. Results show that, under certain condition, our algorithm canimprove sample efficiency by 20% ~ 40%. By combining our framework withon-policy algorithms, RL models can accelerate convergence and obtain betterfinal mean episode rewards especially in complex robotic context whereinteractions are expensive.

Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration