According to cognitive psychology and related disciplines, the development of complex
problem-solving behaviour in biological agents depends on hierarchical cognitive …

We investigated whether deep reinforcement learning (deep RL) is able to synthesize
sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be …

Learning to combine control at the level of joint torques with longer-term goal-directed
behavior is a long-standing challenge for physically embodied artificial agents. Intelligent …

Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked
processes of reinforcement learning: collecting informative experience and inferring optimal …

Reinforcement learning (RL) for continuous control typically employs distributions whose
support covers the entire action space. In this work, we investigate the colloquially known …

In a multi-task learning (MTL) setting, a single model is trained to tackle a diverse set of tasks
jointly. Despite rapid progress in the field, MTL remains challenging due to optimization …

Abstract We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning
algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates …

The advancement of robots, particularly those functioning in complex human-centric
environments, relies on control solutions that are driven by machine learning …

This position paper proposes a fresh look at Reinforcement Learning (RL) from the
perspective of data-efficiency. RL has gone through three major stages: pure on-line RL …

As we deploy reinforcement learning agents to solve increasingly challenging problems,
methods that allow us to inject prior knowledge about the structure of the world and effective …