Related papers: Random Actions vs Random Policies: Bootstrapping M…

When planning with an inaccurate dynamics model, a practical strategy is to restrict planning to regions of state-action space where the model is accurate: also known as a \textit{model precondition}. Empirical real-world trajectory data is…

Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbates this issue. It is impractical to test every policy on…

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…

This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample…

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on…

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…

Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…

While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated…

Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and optimization, and even more so to policies obtained from…

Modern foundation models often undergo iterative ``bootstrapping'' in their post-training phase: a model generates synthetic data, an external verifier filters out low-quality samples, and the high-quality subset is used for further…

We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain…

In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of deep learning algorithms is to automatically construct features well-tuned for the task they try to…

Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is unknown or cannot easily be used for training. In this work, we empirically examine the effects of domain…

Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate. Although there are several existing methods…

In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about…

Bootstrap techniques (also called resampling computation techniques) have introduced new advances in modeling and model evaluation. Using resampling methods to construct a series of new samples which are based on the original data set,…

A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive…

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…

Experiments in predator-prey systems show the emergence of long-term cycles. Deterministic model typically fails in capturing these behaviors, which emerge from the microscopic interplay of individual based dynamics and stochastic effects.…