Related papers: MuDreamer: Learning Predictive World Models withou…
Top-performing Model-Based Reinforcement Learning (MBRL) agents, such as Dreamer, learn the world model by reconstructing the image observations. Hence, they often fail to discard task-irrelevant details and struggle to handle visual…
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses…
A central challenge in image-based Model-Based Reinforcement Learning (MBRL) is to learn representations that distill essential information from irrelevant visual details. While promising, reconstruction-based methods often waste capacity…
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficient solution to robot learning, as it is used to train latent…
The DreamerV3 algorithm recently obtained remarkable performance across diverse environment domains by learning an accurate world model based on Recurrent Neural Networks (RNNs). Following the success of model-based reinforcement learning…
Intelligent agents need to generalize from past experience to achieve goals in complex environments. World models facilitate such generalization and allow learning behaviors from imagined outcomes to increase sample-efficiency. While…
Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning and control. Existing approaches typically employ…
To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the…
We integrate a meta-reinforcement learning algorithm with the DreamerV3 architecture to improve load balancing in operating systems. This approach enables rapid adaptation to dynamic workloads with minimal retraining, outperforming the…
Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly…
The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitations of recurrent…
Developing a general algorithm that learns to solve tasks across a wide range of applications has been a fundamental challenge in artificial intelligence. Although current reinforcement learning algorithms can be readily applied to tasks…
Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…
Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for…
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…
Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional…
3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised…
Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal transformer to predict…
We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building…