Code-Driven Planning in Grid Worlds with Large Language Models

We propose an iterative programmatic planning (IPP) framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code using large language models (LLMs). Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis, where the LLM outputs executable programs that map environment states to action sequences. Our proposed architecture incorporates several prompting strategies, including direct code generation, pseudocode-conditioned refinement, and curriculum-based prompting, but also includes an iterative refinement mechanism that updates code based on task performance feedback. We evaluate our approach using six leading LLMs and two challenging grid-based benchmarks (GRASP and MiniGrid). Our IPP framework demonstrates improvements over direct code generation ranging from 10\% to as much as 10x across five of the six models and establishes a new state-of-the-art result for GRASP. IPP is found to significantly outperform direct elicitation of a solution from GPT-o3-mini (by 63\% on MiniGrid to 116\% on GRASP), demonstrating the viability of the overall approach. Computational costs of all code generation approaches are similar. While code generation has a higher initial prompting cost compared to direct solution elicitation (\$0.08 per task vs. \$0.002 per instance for GPT-o3-mini), the code can be reused for any number of instances, making the amortized cost significantly lower (by 400x on GPT-o3-mini across the complete GRASP benchmark).

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning

Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-generating LLM to induce textual strategies based on advantage estimations and expert demonstrations, and gradually internalizes induced strategies into the RL agent through policy optimization to improve its performance through boosting policy generalization and enhancing sample efficiency. It also provides a direct textual channel to observe and interpret the evolution of the policy's underlying strategies during training. We test DYSTIL over challenging RL environments from Minigrid and BabyAI, and empirically demonstrate that DYSTIL significantly outperforms state-of-the-art baseline methods by 17.75% in average success rate while also enjoying higher sample efficiency during the learning process.

D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection

Current Hierarchical Reinforcement Learning (HRL) algorithms excel in long-horizon sequential decision-making tasks but still face two challenges: delay effects and spurious correlations. To address them, we propose a causal HRL approach called D3HRL. First, D3HRL models delayed effects as causal relationships across different time spans and employs distributed causal discovery to learn these relationships. Second, it employs conditional independence testing to eliminate spurious correlations. Finally, D3HRL constructs and trains hierarchical policies based on the identified true causal relationships. These three steps are iteratively executed, gradually exploring the complete causal chain of the task. Experiments conducted in 2D-MineCraft and MiniGrid show that D3HRL demonstrates superior sensitivity to delay effects and accurately identifies causal relationships, leading to reliable decision-making in complex environments.

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation

Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address the problem of learning such models. In particular, we are interested in a subclass of POMDPs wherein the components of the model, including the observation function, reward function, transition function, and initial state distribution function, can be modeled as low-complexity probabilistic graphical models in the form of a short probabilistic program. Our strategy to learn these programs uses an LLM as a prior, generating candidate probabilistic programs that are then tested against the empirical distribution and adjusted through feedback. We experiment on a number of classical toy POMDP problems, simulated MiniGrid domains, and two real mobile-base robotics search domains involving partial observability. Our results show that using an LLM to guide in the construction of a low-complexity POMDP model can be more effective than tabular POMDP learning, behavior cloning, or direct LLM planning.

World Model Agents with Change-Based Intrinsic Motivation

Sparse reward environments pose a significant challenge for reinforcement learning due to the scarcity of feedback. Intrinsic motivation and transfer learning have emerged as promising strategies to address this issue. Change Based Exploration Transfer (CBET), a technique that combines these two approaches for model-free algorithms, has shown potential in addressing sparse feedback but its effectiveness with modern algorithms remains understudied. This paper provides an adaptation of CBET for world model algorithms like DreamerV3 and compares the performance of DreamerV3 and IMPALA agents, both with and without CBET, in the sparse reward environments of Crafter and Minigrid. Our tabula rasa results highlight the possibility of CBET improving DreamerV3's returns in Crafter but the algorithm attains a suboptimal policy in Minigrid with CBET further reducing returns. In the same vein, our transfer learning experiments show that pre-training DreamerV3 with intrinsic rewards does not immediately lead to a policy that maximizes extrinsic rewards in Minigrid. Overall, our results suggest that CBET provides a positive impact on DreamerV3 in more complex environments like Crafter but may be detrimental in environments like Minigrid. In the latter case, the behaviours promoted by CBET in DreamerV3 may not align with the task objectives of the environment, leading to reduced returns and suboptimal policies.

Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning

In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to prevent unsafe actions. However, because of the large number of false positives, some safe actions are never executed, leading to inadequate exploration in sparse-reward environments. In this work, we aim to learn an efficient state representation to balance the exploration and safety-prefer action in a sparse-reward environment. Firstly, the image input is mapped to latent representation by an auto-encoder. A further contrastive learning objective is employed to distinguish safe and unsafe states. In the learning phase, the latent distance is used to construct an additional safety check, which allows the agent to bias the exploration if it visits an unsafe state. To verify the effectiveness of our method, the experiment is carried out in three navigation-based MiniGrid environments. The result highlights that our method can explore the environment better while maintaining a good balance between safety and efficiency.

ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning

Hyperparameter optimization (HPO) is a billion-dollar problem in machine learning, which significantly impacts the training efficiency and model performance. However, achieving efficient and robust HPO in deep reinforcement learning (RL) is consistently challenging due to its high non-stationarity and computational cost. To tackle this problem, existing approaches attempt to adapt common HPO techniques (e.g., population-based training or Bayesian optimization) to the RL scenario. However, they remain sample-inefficient and computationally expensive, which cannot facilitate a wide range of applications. In this paper, we propose ULTHO, an ultra-lightweight yet powerful framework for fast HPO in deep RL within single runs. Specifically, we formulate the HPO process as a multi-armed bandit with clustered arms (MABC) and link it directly to long-term return optimization. ULTHO also provides a quantified and statistical perspective to filter the HPs efficiently. We test ULTHO on benchmarks including ALE, Procgen, MiniGrid, and PyBullet. Extensive experiments demonstrate that the ULTHO can achieve superior performance with simple architecture, contributing to the development of advanced and automated RL systems.

Induced Modularity and Community Detection for Functionally Interpretable Reinforcement Learning

Interpretability in reinforcement learning is crucial for ensuring AI systems align with human values and fulfill the diverse related requirements including safety, robustness and fairness. Building on recent approaches to encouraging sparsity and locality in neural networks, we demonstrate how the penalisation of non-local weights leads to the emergence of functionally independent modules in the policy network of a reinforcement learning agent. To illustrate this, we demonstrate the emergence of two parallel modules for assessment of movement along the X and Y axes in a stochastic Minigrid environment. Through the novel application of community detection algorithms, we show how these modules can be automatically identified and their functional roles verified through direct intervention on the network weights prior to inference. This establishes a scalable framework for reinforcement learning interpretability through functional modularity, addressing challenges regarding the trade-off between completeness and cognitive tractability of reinforcement learning explanations.

The impact of intrinsic rewards on exploration in Reinforcement Learning

One of the open challenges in Reinforcement Learning is the hard exploration problem in sparse reward environments. Various types of intrinsic rewards have been proposed to address this challenge by pushing towards diversity. This diversity might be imposed at different levels, favouring the agent to explore different states, policies or behaviours (State, Policy and Skill level diversity, respectively). However, the impact of diversity on the agent's behaviour remains unclear. In this work, we aim to fill this gap by studying the effect of different levels of diversity imposed by intrinsic rewards on the exploration patterns of RL agents. We select four intrinsic rewards (State Count, Intrinsic Curiosity Module (ICM), Maximum Entropy, and Diversity is all you need (DIAYN)), each pushing for a different diversity level. We conduct an empirical study on MiniGrid environment to compare their impact on exploration considering various metrics related to the agent's exploration, namely: episodic return, observation coverage, agent's position coverage, policy entropy, and timeframes to reach the sparse reward. The main outcome of the study is that State Count leads to the best exploration performance in the case of low-dimensional observations. However, in the case of RGB observations, the performance of State Count is highly degraded mostly due to representation learning challenges. Conversely, Maximum Entropy is less impacted, resulting in a more robust exploration, despite being not always optimal. Lastly, our empirical study revealed that learning diverse skills with DIAYN, often linked to improved robustness and generalisation, does not promote exploration in MiniGrid environments. This is because: i) learning the skill space itself can be challenging, and ii) exploration within the skill space prioritises differentiating between behaviours rather than achieving uniform state visitation.

A Temporally Correlated Latent Exploration for Reinforcement Learning

Efficient exploration remains one of the longstanding problems of deep reinforcement learning. Instead of depending solely on extrinsic rewards from the environments, existing methods use intrinsic rewards to enhance exploration. However, we demonstrate that these methods are vulnerable to Noisy TV and stochasticity. To tackle this problem, we propose Temporally Correlated Latent Exploration (TeCLE), which is a novel intrinsic reward formulation that employs an action-conditioned latent space and temporal correlation. The action-conditioned latent space estimates the probability distribution of states, thereby avoiding the assignment of excessive intrinsic rewards to unpredictable states and effectively addressing both problems. Whereas previous works inject temporal correlation for action selection, the proposed method injects it for intrinsic reward computation. We find that the injected temporal correlation determines the exploratory behaviors of agents. Various experiments show that the environment where the agent performs well depends on the amount of temporal correlation. To the best of our knowledge, the proposed TeCLE is the first approach to consider the action conditioned latent space and temporal correlation for curiosity-driven exploration. We prove that the proposed TeCLE can be robust to the Noisy TV and stochasticity in benchmark environments, including Minigrid and Stochastic Atari.