Related papers: Trust the Model Where It Trusts Itself -- Model-Ba…
The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle…
Model-based reinforcement learning (MBRL) reduces the cost of real-environment sampling by generating synthetic trajectories (called rollouts) from a learned dynamics model. However, choosing the length of the rollouts poses two dilemmas:…
Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…
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…
Model-based reinforcement learning (MBRL) can reduce interaction cost for autonomous driving by learning a predictive world model, but it typically still depends on task-specific rewards that are difficult to design and often brittle under…
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…
We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and…
In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is…
Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in…
We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms…
The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistants. However, training these agents is severely hampered by…
Hierarchical model-based reinforcement learning (HMBRL) aims to combine the benefits of better sample efficiency of model based reinforcement learning (MBRL) with the abstraction capability of hierarchical reinforcement learning (HRL) to…
Deep Reinforcement Learning (DRL) holds significant promise for achieving human-like Autonomous Vehicle (AV) capabilities, but suffers from low sample efficiency and challenges in reward design. Model-Based Reinforcement Learning (MBRL)…
In this paper an output-feedback model-based reinforcement learning (MBRL) method for a class of second-order nonlinear systems is developed. The control technique uses exact model knowledge and integrates a dynamic state estimator within…
Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious…
Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards. Despite its success, we…
Model-based reinforcement learning (MBRL) methods have shown strong sample efficiency and performance across a variety of tasks, including when faced with high-dimensional visual observations. These methods learn to predict the environment…
Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…
Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgraph Bellman operators, that interpolate between…
Model usage is the central challenge of model-based reinforcement learning. Although dynamics model based on deep neural networks provide good generalization for single step prediction, such ability is over exploited when it is used to…