all AI news
Multi-Stage Episodic Control for Strategic Exploration in Text Games. (arXiv:2201.01251v1 [cs.CL])
Jan. 5, 2022, 2:10 a.m. | Jens Tuyls, Shunyu Yao, Sham Kakade, Karthik Narasimhan
cs.CL updates on arXiv.org arxiv.org
Text adventure games present unique challenges to reinforcement learning
methods due to their combinatorially large action spaces and sparse rewards.
The interplay of these two factors is particularly demanding because large
action spaces require extensive exploration, while sparse rewards provide
limited feedback. This work proposes to tackle the explore-vs-exploit dilemma
using a multi-stage approach that explicitly disentangles these two strategies
within each episode. Our algorithm, called eXploit-Then-eXplore (XTX), begins
each episode using an exploitation policy that imitates a set of …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Data Science Sustainability Co-Op (Summer & Fall 2024)
@ O-I | Perrysburg, OH, United States
Research Scientist
@ Chevron Phillips Chemical Company | USA: Kingwood, TX, US, 77339
Data Scientist Python (Django) (m/f/d)
@ RoomPriceGenie | Hybrid Mannheim, Remote DACH, Remote Germany
Operational Transformation & Strategy - Data Operations - Associate
@ JPMorgan Chase & Co. | Mumbai, Maharashtra, India
Senior Data Scientist
@ Rocket Travel | Chicago, IL USA