In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetrics structure. This paper introduces Quasimetric Reinforcement …
Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them …
Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in …
H Ma, J Wu, N Feng, C Xiao, D Li… - … on Machine Learning, 2024 - openreview.net
Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically …
Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of …
Informational parsimony provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We …
While the maximum entropy (MaxEnt) reinforcement learning (RL) framework--often touted for its exploration and robustness capabilities--is usually motivated from a probabilistic …
Y Liu, B Huang, Z Zhu, H Tian… - Advances in Neural …, 2023 - proceedings.neurips.cc
Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments …
T Ni, B Eysenbach, E Seyedsalehi, M Ma… - arXiv preprint arXiv …, 2024 - arxiv.org
Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes …