We consider the exploration-exploitation trade-off in reinforcement learning and show that an agent endowed with an exponential epistemic-risk-seeking utility function explores efficiently, as measured by regret. The state-action values induced by the exponential utility satisfy a Bellman recursion, so we can use dynamic programming to compute them. We call the resulting algorithm K-learning (for knowledge) and the risk-seeking utility ensures that the associated state-action values (K-values) are optimistic for the expected optimal Q-values under the posterior. The exponential utility function induces a Boltzmann exploration policy for which the'temperature' parameter is equal to the risk-seeking parameter and is carefully controlled to yield a Bayes regret bound of $\tilde O(L^{3/2} \sqrt{S A T})$, where $L$ is the time horizon, $S$ is the number of states, $A$ is the number of actions, and $T$ is the total number of elapsed timesteps. We conclude with a numerical example demonstrating that K-learning is competitive with other state-of-the-art algorithms in practice.

Assuming no prior knowledge or pre-training of the environment safety model given a task, an agent has to learn, via exploration, which states and actions are safe.

Reinforcement learning has gathered much attention in recent years due to its rapid development and rich applications, especially on control systems and robotics. When tackling real-world applications with reinforcement learning method, the corresponded Markov decision process may have huge discrete or even continuous state/action space. Deep reinforcement learning has been studied for handling these issues through deep learning for years, and one promising branch is the actor-critic architecture. Many past studies leveraged multiple critics to enhance the accuracy of evaluation of a policy for addressing the overestimation and underestimation issues. However, few studies have considered the architecture with multiple actors together with multiple critics. This study proposes a novel multi-actor multi-critic (MAMC) deep deterministic reinforcement learning method. The proposed method has three main features, including selection of actors based on non-dominated sorting for exploration with respect to skill and creativity factors, evaluation for actors and critics using a quantile-based ensemble strategy, and exploiting actors with best skill factor. Theoretical analysis proves the learning stability and bounded estimation bias for the MAMC. The present study examines the performance on a well-known reinforcement learning benchmark MuJoCo. Experimental results show that the proposed framework outperforms state-of-the-art deep deterministic based reinforcement learning methods. Experimental analysis also indicates the proposed components are effective. Empirical analysis further investigates the validity of the proposed method, and shows its benefit on complicated problems. The source code can be found at https://github.com/AndyWu101/MAMC.

Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancement in boosting Large Language Models (LLMs) to solve complex tasks in digital domains. However, the potential of slow thinking remains largely unexplored for robotic foundation models interacting with the physical world. In this work, we propose Hume: a dual-system Vision-Language-Action (VLA) model with value-guided System-2 thinking and cascaded action denoising, exploring human-like thinking capabilities of Vision-Language-Action models for dexterous robot control. System 2 of Hume implements value-Guided thinking by extending a Vision-Language-Action Model backbone with a novel value-query head to estimate the state-action value of predicted actions. The value-guided thinking is conducted by repeat sampling multiple action candidates and selecting one according to state-action value. System 1 of Hume is a lightweight reactive visuomotor policy that takes System 2 selected action and performs cascaded action denoising for dexterous robot control. At deployment time, System 2 performs value-guided thinking at a low frequency while System 1 asynchronously receives the System 2 selected action candidate and predicts fluid actions in real time. We show that Hume outperforms the existing state-of-the-art Vision-Language-Action models across multiple simulation benchmark and real-robot deployments.

Collusion in market pricing is a concept associated with human actions to raise market prices through artificially limited supply. Recently, the idea of algorithmic collusion was put forward, where the human action in the pricing process is replaced by automated agents. Although experiments have shown that collusive market equilibria can be reached through such techniques, without the need for human intervention, many of the techniques developed remain susceptible to exploitation by other players, making them difficult to implement in practice. In this article, we explore a situation where an agent has a multi-objective strategy, and not only learns to unilaterally exploit market dynamics originating from other algorithmic agents, but also learns to model the behaviour of other agents directly. Our results show how common critiques about the viability of algorithmic collusion in real-life settings can be overcome through the usage of slightly more complex algorithms.

We consider the exploration-exploitation trade-off in reinforcement learning and show that an agent endowed with an exponential epistemic-risk-seeking utility function explores efficiently, as measured by regret. The state-action values induced by the exponential utility satisfy a Bellman recursion, so we can use dynamic programming to compute them. We call the resulting algorithm K-learning (for knowledge) and the risk-seeking utility ensures that the associated state-action values (K-values) are optimistic for the expected optimal Q-values under the posterior. The exponential utility function induces a Boltzmann exploration policy for which the'temperature' parameter is equal to the risk-seeking parameter and is carefully controlled to yield a Bayes regret bound of \tilde O(L {3/2} \sqrt{S A T}), where L is the time horizon, S is the number of states, A is the number of actions, and T is the total number of elapsed timesteps. We conclude with a numerical example demonstrating that K-learning is competitive with other state-of-the-art algorithms in practice.

The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be considered ``undesirable" or ``unethical. Without thorough understanding of the incentives a reward function creates, it can be difficult to impose principled yet general control mechanisms over its behavior. In this paper, we study methods for constructing guardrails for AI agents that use reward functions to learn decision making. We introduce a novel approach, which we call strategy masking, to explicitly learn and then suppress undesirable AI agent behavior. We apply our method to study lying in AI agents and show that strategy masking can effectively modify agent behavior by suppressing, or actively penalizing, the reward dimension for lying such that agents act more honestly while not compromising their ability to perform effectively.