Sciweavers

949 search results - page 73 / 190
» Can Doxastic Agents Learn
Sort
View
GECCO
2007
Springer
214views Optimization» more  GECCO 2007»
15 years 7 months ago
Portfolio allocation using XCS experts in technical analysis, market conditions and options market
Schulenburg [15] first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff [12] investigat...
Sor Ying (Byron) Wong, Sonia Schulenburg
IUI
1998
ACM
15 years 5 months ago
Coherent Gestures, Locomotion, and Speech in Life-like Pedagogical Agents
Life-likeanimatedinterfaceagentsforknowledge-basedlearning environments can provide timely, customized advice to support students’ problem solving. Because of their strong visua...
Stuart G. Towns, Jennifer L. Voerman, Charles B. C...
GECCO
2006
Springer
133views Optimization» more  GECCO 2006»
15 years 4 months ago
On-line evolutionary computation for reinforcement learning in stochastic domains
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
Shimon Whiteson, Peter Stone
103
Voted
ML
1998
ACM
117views Machine Learning» more  ML 1998»
15 years 14 days ago
Learning Team Strategies: Soccer Case Studies
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy, but may behave di erently due to position-dependent inputs. All...
Rafal Salustowicz, Marco Wiering, Jürgen Schm...
ISDA
2009
IEEE
15 years 7 months ago
Postponed Updates for Temporal-Difference Reinforcement Learning
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Harm van Seijen, Shimon Whiteson