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 this paper, a novel racing environment for OpenAI Gym is introduced. Thisenvironment operates with continuous action- and state-spaces and requiresagents to learn to control the acceleration and steering of a car whilenavigating a randomly generated racetrack. Different versions of twoactor-critic learning algorithms are tested on this environment: Sampled PolicyGradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG isintroduced that aims to improve learning performance by weighting actionsamples during the policy update step. The effect of using experience replay(ER) is also investigated. To this end, a modification to PPO is introducedthat allows for training using old action samples by optimizing the actor inlog space. Finally, a new technique for performing ER is tested that aims toimprove learning speed without sacrificing performance by splitting thetraining into two parts, whereby networks are first trained using statetransitions from the replay buffer, and then using only recent experiences. Theresults indicate that experience replay is not beneficial to PPO in continuousaction spaces. The training of SPG seems to be more stable when actions areweighted. All versions of SPG outperform PPO when ER is used. The ER trick iseffective at improving training speed on a computationally less intensiveversion of SPG.

Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO