Related papers: Variational Model-based Policy Optimization

This work shows that value-aware model learning, known for its numerous theoretical benefits, is also practically viable for solving challenging continuous control tasks in prevalent model-based reinforcement learning algorithms. First, we…

Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the lens of robust Markov decision processes (RMDPs), which…

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in…

Model Predictive Control (MPC)-based Reinforcement Learning (RL) offers a structured and interpretable alternative to Deep Neural Network (DNN)-based RL methods, with lower computational complexity and greater transparency. However,…

Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g.,…

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

Multi-robot systems can benefit from reinforcement learning (RL) algorithms that learn behaviours in a small number of trials, a property known as sample efficiency. This research thus investigates the use of learned world models to improve…

Reinforcement learning (RL) has been successfully applied to solve the problem of finding obstacle-free paths for autonomous agents operating in stochastic and uncertain environments. However, when the underlying stochastic dynamics of the…

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…

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a…

Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict…

It is challenging for reinforcement learning (RL) algorithms to succeed in real-world applications like financial trading and logistic system due to the noisy observation and environment shifting between training and evaluation. Thus, it…

Real-world decision-making problems are often marked by complex, uncertain dynamics that can shift or break under changing conditions. Traditional Model-Based Reinforcement Learning (MBRL) approaches learn predictive models of environment…

Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and…

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

Applying probabilistic models to reinforcement learning (RL) enables the application of powerful optimisation tools such as variational inference to RL. However, existing inference frameworks and their algorithms pose significant challenges…

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is…

In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the…