Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes.

We argue that these properties are satisfied in many continuous state-action Markov decision processes.

Instead, wesuggest that foragivenCMP,it is natural to be interested in Markov rewards, but acknowledge the importance of going beyond such functions.

RL-as-inference (see discussion in Section 4.3), they differ crucially in how the objective is interpreted.

Modern reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of state-actions or simple models such as linearly modeled state-action value functions. To derive RL policies that efficiently handle large state-action spaces with more general value functions, some recent works have considered nonlinear function approximation using kernel ridge regression. We propose $\pi$-KRVI, an optimistic modification of least-squares value iteration, when the action-value function is represented by an RKHS. We prove the first order-optimal regret guarantees under a general setting. Our results show a significant polynomial in the number of episodes improvement over the state of the art. In particular, with highly non-smooth kernels (such as Neural Tangent kernel or some Matérn kernels) the existing results lead to trivial (superlinear in the number of episodes) regret bounds. We show a sublinear regret bound that is order optimal in the cases where a lower bound on regret is known (which includes the kernels mentioned above).

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task performance, while those that prioritize reward leave safety constraints frequently violated, producing diffuse cost landscapes that flatten gradients and stall policy improvement. We introduce the Uncertain Safety Critic (USC), a novel approach that integrates uncertainty-aware modulation and refinement into critic training. By concentrating conservatism in uncertain and costly regions while preserving sharp gradients in safe areas, USC enables policies to achieve effective reward-safety trade-offs. Extensive experiments show that USC reduces safety violations by approximately 40% while maintaining competitive or higher rewards, and reduces the error between predicted and true cost gradients by approximately 83%, breaking the prevailing trade-off between safety and performance and paving the way for scalable safe RL.

Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes.

We argue that these properties are satisfied in many continuous state-action Markov decision processes.