Recent Advances in Hierarchical Reinforcement Learning
Discrete Event Dynamic Systems
Reinforcement learning for POMDPs based on action values and stochastic optimization
Eighteenth national conference on Artificial intelligence
Agent programming via planning programs
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Improving the performance of complex agent plans through reinforcement learning
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Reinforcement learning through global stochastic search in N-MDPs
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II
Hi-index | 0.00 |
We propose a method to generate agent controllers, represented as state machines, to act in partially observable environments. Such controllers are used to constrain the search space, applying techniques from Hierarchical Reinforcement Learning. We define a multi-step process, in which a simulator is employed to generate possible traces of execution. Those traces are then utilized to induce a non-deterministic state machine, that represents all reasonable behaviors, given the approximate models and planners used in simulation. The state machine will have multiple possible choices in some of its states. Those states are choice points, and we defer the learning of those choices to the deployment of the agent in the actual environment. The controller obtained can therefore adapt to the actual environment, limiting the search space in a sensible way.