In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploration, or approximate expert trajectories when rewards are sparse. In this paper, we propose an algorithmic scheme that can handle a wide class of constraints in RL tasks: specifically, any constraints that require expected values of some vector measurements (such as the use of an action) to lie in a convex set. This captures previously studied constraints (such as safety and proximity to an expert), but also enables new classes of constraints (such as diversity). Our approach comes with rigorous theoretical guarantees and only relies on the ability to approximately solve standard RL tasks. As a result, it can be easily adapted to work with any model-free or model-based RL. In our experiments, we show that it matches previous algorithms that enforce safety via constraints, but can also enforce new properties that these algorithms do not incorporate, such as diversity.

Generalization in image-based reinforcement learning (RL) aims to learn a robust policy that could be applied directly on unseen visual environments, which is a challenging task since agents usually tend to overfit to their training environment. To handle this problem, a natural approach is to increase the data diversity by image based augmentations. However, different with most vision tasks such as classification and detection, RL tasks are not always invariant to spatial based augmentations due to the entanglement of environment dynamics and visual appearance. In this paper, we argue with two principles for augmentations in RL: First, the augmented observations should facilitate learning a universal policy, which is robust to various distribution shifts. Second, the augmented data should be invariant to the learning signals such as action and reward. Following these rules, we revisit image-based RL tasks from the view of frequency domain and propose a novel augmentation method, namely Spectrum Random Masking (SRM),which is able to help agents to learn the whole frequency spectrum of observation for coping with various distributions and compatible with the pre-collected action and reward corresponding to original observation. Extensive experiments conducted on DMControl Generalization Benchmark demonstrate the proposed SRM achieves the state-of-the-art performance with strong generalization potentials.

Time-inhomogeneous finite-horizon Markov decision processes (MDP) are frequently employed to model decision-making in dynamic treatment regimes and other statistical reinforcement learning (RL) scenarios. These fields, especially healthcare and business, often face challenges such as high-dimensional state spaces and time-inhomogeneity of the MDP process, compounded by insufficient sample availability which complicates informed decision-making. To overcome these challenges, we investigate knowledge transfer within time-inhomogeneous finite-horizon MDP by leveraging data from both a target RL task and several related source tasks. We have developed transfer learning (TL) algorithms that are adaptable for both batch and online $Q$-learning, integrating valuable insights from offline source studies. The proposed transfer $Q$-learning algorithm contains a novel {\em re-targeting} step that enables {\em cross-stage transfer} along multiple stages in an RL task, besides the usual {\em cross-task transfer} for supervised learning. We establish the first theoretical justifications of TL in RL tasks by showing a faster rate of convergence of the $Q^*$-function estimation in the offline RL transfer, and a lower regret bound in the offline-to-online RL transfer under stage-wise reward similarity and mild design similarity across tasks. Empirical evidence from both synthetic and real datasets is presented to evaluate the proposed algorithm and support our theoretical results.

Large Language Models (LLMs) are now widely used across many domains. With their rapid development, Reinforcement Learning with V erifiable Rewards (RL VR) has surged in recent months to enhance their reasoning and understanding abilities. However, its complex data flows, and diverse tasks pose substantial challenges to RL training systems, and there is limited understanding of RL VR from a system perspective. To thoroughly understand the system challenges introduced by RL VR, we present a characterization study of RL VR tasks in our LLM deployment. Specifically, we investigate the distribution and variation trends of workloads across different RL tasks across training steps. We identify issues such as GPU idling caused by skewed sequence length distribution, inefficient parallel strategies in dynamically varying workloads, inefficient data management mechanisms, and load imbalance. We describe our observations and call for further investigation into the remaining open challenges. Furthermore, we propose PolyTrace benchmark suite to conduct evaluation with realistic workloads, a practical use case validates that PolyTrace benchmark suite exhibits 94.7% accuracy.

We thank the reviewers for their constructive comments. Here we will focus on the main concerns. This is a neuroscientific finding, which has been reviewed in e.g. Feedback alignment fails on simple problems and is known not work at all in deeper networks. AGREL dealt with a single hidden layer.

The high variance stems from the lack of structural credit assignment, i.e. a single scalar