Large language models (LLMs) have demonstrated high performance on tasks expressed in natural language, particularly in zero- or few-shot settings. These are typically framed as supervised (e.g., classification) or unsupervised (e.g., clustering) problems. However, limited work evaluates LLMs as agents in reinforcement learning (RL) tasks (e.g., playing games), where learning occurs through interaction with an environment and a reward system. While prior work focused on representing tasks that rely on a language representation, we study structured, non-linguistic reasoning - such as interpreting positions in a grid world. We therefore introduce PARL (Prompt-based Agent for Reinforcement Learning), a method that uses LLMs as RL agents through prompting, without any fine-tuning. PARL encodes actions, states, and rewards in the prompt, enabling the model to learn through trial-and-error interaction. We evaluate PARL on three standard RL tasks that do not entirely rely on natural language. We show that it can match or outperform traditional RL agents in simple environments by leveraging pretrained knowledge. However, we identify performance limitations in tasks that require complex mathematical operations or decoding states and actions.

Preference-based reinforcement learning has gained prominence as a strategy for training agents in environments where the reward signal is difficult to specify or misaligned with human intent. However, its effectiveness is often limited by the high cost and low availability of reliable human input, especially in domains where expert feedback is scarce or errors are costly. To address this, we propose a novel framework that combines two complementary strategies: probabilistic crowd modelling to handle noisy, multi-annotator feedback, and active learning to prioritize feedback on the most informative agent actions. We extend the Advise algorithm to support multiple trainers, estimate their reliability online, and incorporate entropy-based query selection to guide feedback requests. We evaluate our approach in a set of environments that span both synthetic and real-world-inspired settings, including 2D games (Taxi, Pacman, Frozen Lake) and a blood glucose control task for Type 1 Diabetes using the clinically approved UVA/Padova simulator. Our preliminary results demonstrate that agents trained with feedback on uncertain trajectories exhibit faster learning in most tasks, and we outperform the baselines for the blood glucose control task.

Large Language Models (LLMs) show potential as sequential decision-making agents, but their application is often limited due to a reliance on large, computationally expensive models. This creates a need to improve smaller models, yet existing post-training methods are designed for single-turn interactions and cannot handle credit assignment in multi-step agentic tasks. To address this, we introduce Multi-Step Group-Relative Policy Optimization (MS-GRPO), a new algorithm for post-training LLM agents, grounded in formal Text-Mediated Stochastic Game (TSMG) and Language-Agent Policy (LAP) frameworks. For credit assignment, MS-GRPO attributes the entire cumulative episode reward to each individual episode step. We supplement this algorithm with a novel absolute-advantage-weighted episode sampling strategy that we show improves training performance. We evaluate our approach by post-training a 3-billion parameter model on Snake and Frozen Lake. Our experiments demonstrate that the method is effective in improving decision-making performance: our post-trained 3B parameter model outperforms a 72B parameter baseline by 50% on the Frozen Lake task. This work demonstrates that targeted post-training is a practical and efficient alternative to relying on model scale for creating sequential decision-making agents using LLMs.

Quantum Computing aims to streamline machine learning, making it more effective with fewer trainable parameters. This reduction of parameters can speed up the learning process and reduce the use of computational resources. However, in the current phase of quantum computing development, known as the noisy intermediate-scale quantum era (NISQ), learning is difficult due to a limited number of qubits and widespread quantum noise. To overcome these challenges, researchers are focusing on variational quantum circuits (VQCs). VQCs are hybrid algorithms that merge a quantum circuit, which can be adjusted through parameters, with traditional classical optimization techniques. These circuits require only few qubits for effective learning. Recent studies have presented new ways of applying VQCs to reinforcement learning, showing promising results that warrant further exploration. This study investigates the effects of various techniques -- data re-uploading, input scaling, output scaling -- and introduces exponential learning rate decay in the quantum proximal policy optimization algorithm's actor-VQC. We assess these methods in the popular Frozen Lake and Cart Pole environments. Our focus is on their ability to reduce the number of parameters in the VQC without losing effectiveness. Our findings indicate that data re-uploading and an exponential learning rate decay significantly enhance hyperparameter stability and overall performance. While input scaling does not improve parameter efficiency, output scaling effectively manages greediness, leading to increased learning speed and robustness.

Reinforcement learning (RL) is a subset of artificial intelligence (AI) where agents learn the best action by interacting with the environment, making it suitable for tasks that do not require labeled data or direct supervision. Hyperparameters (HP) tuning refers to choosing the best parameter that leads to optimal solutions in RL algorithms. Manual or random tuning of the HP may be a crucial process because variations in this parameter lead to changes in the overall learning aspects and different rewards. In this paper, a novel and automatic HP-tuning method called Q-FOX is proposed. This uses both the FOX optimizer, a new optimization method inspired by nature that mimics red foxes' hunting behavior, and the commonly used, easy-to-implement RL Q-learning algorithm to solve the problem of HP tuning. Moreover, a new objective function is proposed which prioritizes the reward over the mean squared error (MSE) and learning time (steps). Q-FOX has been evaluated on two OpenAI Gym environment control tasks: Cart Pole and Frozen Lake. It exposed greater cumulative rewards than HP tuning with other optimizers, such as PSO, GA, Bee, or randomly selected HP. The cumulative reward for the Cart Pole task was 32.08, and for the Frozen Lake task was 0.95. Despite the robustness of Q-FOX, it has limitations. It cannot be used directly in real-word problems before choosing the HP in a simulation environment because its processes work iteratively, making it time-consuming. The results indicate that Q-FOX has played an essential role in HP tuning for RL algorithms to effectively solve different control tasks.

Multi-task reinforcement learning and meta-reinforcement learning have been developed to quickly adapt to new tasks, but they tend to focus on tasks with higher rewards and more frequent occurrences, leading to poor performance on tasks with sparse rewards. To address this issue, GFlowNets can be integrated into meta-learning algorithms (GFlowMeta) by leveraging the advantages of GFlowNets on tasks with sparse rewards. However, GFlowMeta suffers from performance degradation when encountering heterogeneous transitions from distinct tasks. To overcome this challenge, this paper proposes a personalized approach named pGFlowMeta, which combines task-specific personalized policies with a meta policy. Each personalized policy balances the loss on its personalized task and the difference from the meta policy, while the meta policy aims to minimize the average loss of all tasks. The theoretical analysis shows that the algorithm converges at a sublinear rate. Extensive experiments demonstrate that the proposed algorithm outperforms state-of-the-art reinforcement learning algorithms in discrete environments.