Rode: Learning roles to decompose multi-agent tasks
Estimating q (s, s') with deep deterministic dynamics gradients
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 …
utility of transitioning from a state $ s $ to a neighboring state $ s'$ and then acting optimally …
Know your action set: Learning action relations for reinforcement learning
Intelligent agents can solve tasks in various ways depending on their available set of
actions. However, conventional reinforcement learning (RL) assumes a fixed action set. This …
actions. However, conventional reinforcement learning (RL) assumes a fixed action set. This …
Learning agent representations for ice hockey
Team sports is a new application domain for agent modeling with high real-world impact. A
fundamental challenge for modeling professional players is their large number (over 1K) …
fundamental challenge for modeling professional players is their large number (over 1K) …
A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning
Transfer learning (TL) has shown great potential to improve Reinforcement Learning (RL)
efficiency by leveraging prior knowledge in new tasks. However, much of the existing TL …
efficiency by leveraging prior knowledge in new tasks. However, much of the existing TL …
Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning
Transferring knowledge in cross-domain reinforcement learning is a challenging setting in
which learning is accelerated by reusing knowledge from a task with different observation …
which learning is accelerated by reusing knowledge from a task with different observation …