Abstract: We present a new reinforcement learning (RL) approach that enables an autonomous agent to solve decision making problems under constraints.
Abstract: We present a new reinforcement learning (RL) approach that enables an autonomous agent to solve decision making problems under constraints.
This work presents a new reinforcement learning (RL) approach that enables an autonomous agent to solve decision making problems under constraints and ...
These formally verified abstract policies are then used to restrict the RL agent's exploration of the solution space so as to avoid constraint violations. We ...
Original language, English. Title of host publication, 9th International Conference on Agents and Artificial Intelligence (ICAART).
Although increasingly successful, RL cannot be used in applications where unpredictable agent behaviour may have significant unintended negative consequences.
Assured Reinforcement Learning with Formally Verified Abstract Policies. In Proc. 9th International Conference on Agents and Artificial Intelligence (ICAART ...
No information is available for this page. · Learn why
Assured Reinforcement Learning with Formally Verified Abstract Policies. George Rupert Mason, Radu Constantin Calinescu, Daniel Kudenko, Alec Banks. Computer ...
May 26, 2018 · We present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that ...