1 code implementation • 21 Feb 2020 • Ashley D. Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski
In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
no code implementations • 20 May 2019 • Ashley D. Edwards, Charles L. Isbell
Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos.
2 code implementations • 21 May 2018 • Ashley D. Edwards, Himanshu Sahni, Yannick Schroecker, Charles L. Isbell
In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations.
no code implementations • 27 Mar 2018 • Ashley D. Edwards, Laura Downs, James C. Davidson
If we relax this one restriction and endow the agent with knowledge of the reward function, and in particular of the goal, we can leverage backwards induction to accelerate training.
no code implementations • 21 Nov 2017 • Ashley D. Edwards, Charles L. Isbell Jr
A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances.
General Reinforcement Learning Generative Adversarial Network +2
no code implementations • 25 May 2017 • Ashley D. Edwards, Srijan Sood, Charles L. Isbell Jr
One problem with this approach is that we typically need to redefine the rewards each time the goal changes, which often requires some understanding of the solution in the agents environment.