Related papers: Value Memory Graph: A Graph-Structured World Model…
It is a long-standing question to discover causal relations among a set of variables in many empirical sciences. Recently, Reinforcement Learning (RL) has achieved promising results in causal discovery from observational data. However,…
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of…
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…
Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…
Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully…
Humans leverage rich internal models of the world to reason about the future, imagine counterfactuals, and adapt flexibly to new situations. In Reinforcement Learning (RL), world models aim to capture how the environment evolves in response…
Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the…
Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…
World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…
In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability…
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an agent needs to learn short-term memories of relevant…
Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve…
Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its…
Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code…
Dynamic mechanism design studies how mechanism designers should allocate resources among agents in a time-varying environment. We consider the problem where the agents interact with the mechanism designer according to an unknown Markov…
Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…
The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing…
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a…
Offline reinforcement learning algorithms hold the promise of enabling data-driven RL methods that do not require costly or dangerous real-world exploration and benefit from large pre-collected datasets. This in turn can facilitate…