Related papers: Policy-Value Alignment and Robustness in Search-ba…

Autonomous agents often require multiple strategies to solve complex tasks, but determining when to switch between strategies remains challenging. This research introduces a reinforcement learning technique to learn switching thresholds…

Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…

Gradient-based learning in multi-agent systems is difficult because the gradient derives from a first-order model which does not account for the interaction between agents' learning processes. LOLA (arXiv:1709.04326) accounts for this by…

The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's value function prediction compared to the…

Improving the decision-making capabilities of agents is a key challenge on the road to artificial intelligence. To improve the planning skills needed to make good decisions, MuZero's agent combines prediction by a network model and planning…

Many of the strongest game playing programs use a combination of Monte Carlo tree search (MCTS) and deep neural networks (DNN), where the DNNs are used as policy or value evaluators. Given a limited budget, such as online playing or during…

AlphaZero-like Monte Carlo Tree Search systems, originally introduced for two-player games, dynamically balance exploration and exploitation using neural network guidance. This combination makes them also suitable for classical search…

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further…

Since vision-based manipulation policies are typically trained from data gathered from a single viewpoint, their performance drops when the view changes during deployment. Naively aggregating demonstrations from numerous random views is not…

Understanding citizens' values in participatory systems is crucial for citizen-centric policy-making. We envision a hybrid participatory system where participants make choices and provide motivations for those choices, and AI agents…

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

Though intelligent agents are supposed to improve human experience (or make it more efficient), it is hard from a human perspective to grasp the ethical values which are explicitly or implicitly embedded in an agent behaviour. This is the…

Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is…

In the past few years, AlphaZero's exceptional capability in mastering intricate board games has garnered considerable interest. Initially designed for the game of Go, this revolutionary algorithm merges deep learning techniques with the…

While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…

The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction. Since collecting policy rollouts in the real world is expensive, we investigate whether a…

While deep reinforcement learning has achieved tremendous successes in various applications, most existing works only focus on maximizing the expected value of total return and thus ignore its inherent stochasticity. Such stochasticity is…

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance. However, the gradient conflict problem is…

Visual exploration and smart data collection via autonomous vehicles is an attractive topic in various disciplines. Disturbances like wind significantly influence both the power consumption of the flying robots and the performance of the…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…