Related papers: Dream to Control: Learning Behaviors by Latent Ima…

Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the environment. However, without appropriate knowledge and…

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…

Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In…

How can artificial agents learn to solve many diverse tasks in complex visual environments in the absence of any supervision? We decompose this question into two problems: discovering new goals and learning to reliably achieve them. We…

Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks…

Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by learning interactive world models, these agents tend to be…

The paradigm of learning-based robotics holds immense promise, yet its translation to real-world applications is critically hindered by the sample inefficiency and brittleness of conventional model-free reinforcement learning algorithms. In…

The Overfitted Brain hypothesis suggests dreams happen to allow generalization in the human brain. Here, we ask if the same is true for reinforcement learning agents as well. Given limited experience in a real environment, we use…

Autonomous robots need to be able to adapt to unforeseen situations and to acquire new skills through trial and error. Reinforcement learning in principle offers a suitable methodological framework for this kind of autonomous learning.…

The Dreamer algorithm has recently obtained remarkable performance across diverse environment domains by training powerful agents with simulated trajectories. However, the compressed nature of its world model's latent space can result in…

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models…

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios such as autonomous driving, there commonly exists noncontrollable dynamics independent of the action signals, making it…

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner…

Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to…

Capturing human learning behavior based on deep learning methods has become a major research focus in both psychology and intelligent systems. Recent approaches rely on controlled experiments or rule-based models to explore cognitive…

Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong potential in handling these challenges while remaining…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

The DreamerV3 agent recently demonstrated state-of-the-art performance in diverse domains, learning powerful world models in latent space using a pixel reconstruction loss. However, while the reconstruction loss is essential to Dreamer's…

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…