arXiv AI
Jun 16
Safe Exploration via Policy Priors
arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.
All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learning
arXiv:2606. 01363v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data efficient and safe learning in robotics.
Related stories
arXiv AI
Jun 10
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
arXiv:2606. 10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains.
arXiv Machine Learning
Aug 11
Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics
arXiv:2604. 26836v3 Announce Type: replace Abstract: Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploration, yet their reliance on first-principles models or Gaussian processes limits scalability and broader applicability.
arXiv AI
Jul 17
RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
Hugging Face Trending Papers
Jul 8
Safe Reinforcement Learning using Ideas from Model Predictive Control
Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics. A persistent challenge, however, is ensuring strict, hard safety constraints during the active learning phase.
arXiv AI
Jun 8
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
arXiv:2606. 06976v1 Announce Type: new Abstract: Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct responses, which may accumulate errors throughout multi-step interactions.
arXiv AI
Aug 21
Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
arXiv:2608. 19836v1 Announce Type: cross Abstract: Probabilistic shielding is a technique for safe reinforcement learning (RL).
arXiv Machine Learning
Jul 9
Safe Reinforcement Learning using Ideas from Model Predictive Control
arXiv:2607. 07252v1 Announce Type: new Abstract: Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics.
arXiv AI
Sep 1
Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration
The paper introduces OHCAM, an online method for learning action models that include conditional and quantified effects from limited interactions. It maintains a belief over possible models and actively chooses actions that maximize disagreement among hypotheses to reduce uncertainty, while handling noisy observations. Starting with simple hypotheses, OHCAM expands complexity only when necessary, achieving sample‑efficient learning that outperforms baselines on benchmark domains and is validated on a Kinova Gen3 robot.
arXiv AI
Jun 2
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
arXiv:2606. 00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets.
arXiv Machine Learning
Sep 1
Uncertainty-Driven Replay Memory for Reinforcement Learning
The paper introduces Uncertainty-Driven Replay Memory (UDRM), a new experience replay buffer for reinforcement learning that prioritizes storing transitions with high uncertainty estimates. Unlike traditional buffers that rely on temporal difference error or transition distributions, UDRM updates its contents based on uncertainty derived from the RL model during training. Experiments show that this uncertainty-aware buffer leads to higher rewards during training compared to other uncertainty-aware RL frameworks.
arXiv Machine Learning
Aug 24
Smart Exploration in Reinforcement Learning using Bounded Uncertainty Models
The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.