Related papers: Hierarchical Policy Learning is Sensitive to Goal …
Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities.…
Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control…
Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learning yet even a tiny…
Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the…
This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with…
In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws…
To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant…
Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer. In control theory, prioritized composition is realized by null-space…
The high-dimensional or sparse reward task of a reinforcement learning (RL) environment requires a superior potential controller such as hierarchical reinforcement learning (HRL) rather than an atomic RL because it absorbs the complexity of…
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstraction in the action space. Ideally, these options can be…
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained to perform them. Instead, they are usually trained end-to-end, with the hope being that useful skills will…
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…
Reinforcement learning algorithms struggle on tasks with complex hierarchical dependency structures. Humans and other intelligent agents do not waste time assessing the utility of every high-level action in existence, but instead only…
Model-based planners and controllers are commonly used to solve complex manipulation problems as they can efficiently optimize diverse objectives and generalize to long horizon tasks. However, they often fail during deployment due to noisy…
Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its…
Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…
Legged robots must exhibit robust and agile locomotion across diverse, unstructured terrains, a challenge exacerbated under blind locomotion settings where terrain information is unavailable. This work introduces a hierarchical…
Diffusion policies have shown impressive results in robot imitation learning, even for tasks that require satisfaction of kinematic equality constraints. However, task performance alone is not a reliable indicator of the policy's ability to…
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…