Developing cooperative policies for multi-stage reinforcement learning tasks

no code implementations • 11 May 2022 • Jordan Erskine, Chris Lehnert

Many hierarchical reinforcement learning algorithms utilise a series of independent skills as a basis to solve tasks at a higher level of reasoning.

Hierarchical Reinforcement Learning reinforcement-learning +1

Developing cooperative policies for multi-stage tasks

no code implementations • 1 Jul 2020 • Jordan Erskine, Chris Lehnert

This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task.

Reinforcement Learning (RL)