An unsupervised autonomous learning framework for goal-directed behaviours in dynamic contexts.
(2022)
Journal Article
EZENKWU, C.P. and STARKEY, A. 2022. An unsupervised autonomous learning framework for goal-directed behaviours in dynamic contexts. Advances in computational intelligence [online], 2(3), article number 26. Available from: https://doi.org/10.1007/s43674-022-00037-9
Due to their dependence on a task-specific reward function, reinforcement learning agents are ineffective at responding to a dynamic goal or environment. This paper seeks to overcome this limitation of traditional reinforcement learning through a tas... Read More about An unsupervised autonomous learning framework for goal-directed behaviours in dynamic contexts..