The robust constrained Markov decision process (RCMDP) is a recent
task-...
In off-policy reinforcement learning, a behaviour policy performs explor...
The challenge of language grounding is to fully understand natural langu...
Purpose of review: This paper reviews opportunities and challenges for
d...
In reinforcement learning (RL), an agent must explore an initially unkno...
Quality-Diversity (QD) algorithms evolve behaviourally diverse and
high-...
A long-standing challenge in artificial intelligence is lifelong learnin...
In Quality-Diversity (QD) algorithms, which evolve a behaviourally diver...
Rapid performance recovery from unforeseen environmental perturbations
r...
The energy of ocean waves is the key distinguishing factor of a marine
e...
In swarm robotics, any of the robots in a swarm may be affected by diffe...