In planning and reinforcement learning, the identification of common subgoal structures across problems is important when goals are to be achieved over long horizons. Recently, it has been shown that such structures can be expressed as feature-based rules, called sketches, over a number of classical planning domains. These sketches split problems into subproblems which then become solvable in low polynomial time by a greedy sequence of IW$(k)$ searches. Methods for learning sketches using feature pools and min-SAT solvers have been developed, yet they face two key limitations: scalability and expressivity. In this work, we address these limitations by formulating the problem of learning sketch decompositions as a deep reinforcement learning (DRL) task, where general policies are sought in a modified planning problem where the successor states of a state s are defined as those reachable from s through an IW$(k)$ search. The sketch decompositions obtained through this method are experimentally evaluated across various domains, and problems are regarded as solved by the decomposition when the goal is reached through a greedy sequence of IW$(k)$ searches. While our DRL approach for learning sketch decompositions does not yield interpretable sketches in the form of rules, we demonstrate that the resulting decompositions can often be understood in a crisp manner.
In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's adaptability across diverse control tasks. At its core, an RL agent seeks to maximize its cumulative reward, enabling AI algorithms to uncover novel solutions previously unknown to experts. However, this focus on reward maximization also introduces a significant difficulty: improper reward specification can result in unexpected, misaligned agent behavior and inefficient learning. The complexity of accurately specifying the reward function is further amplified by the sequential nature of the task, the sparsity of learning signals, and the multifaceted aspects of the desired behavior. In this thesis, we survey the literature on effective reward specification strategies, identify core challenges relating to each of these approaches, and propose original contributions addressing the issue of sample efficiency and alignment in deep reinforcement learning. Reward specification represents one of the most challenging aspects of applying reinforcement learning in real-world domains. Our work underscores the absence of a universal solution to this complex and nuanced challenge; solving it requires selecting the most appropriate tools for the specific requirements of each unique application.
A reinforcement learning-enhanced genetic algorithm (RLGA) is proposed for wind farm layout optimization (WFLO) problems. While genetic algorithms (GAs) are among the most effective and accessible methods for WFLO, their performance and convergence are highly sensitive to parameter selections. To address the issue, reinforcement learning (RL) is introduced to dynamically select optimal parameters throughout the GA process. To illustrate the accuracy and efficiency of the proposed RLGA, we evaluate the WFLO problem for four layouts (aligned, staggered, sunflower, and unstructured) under unidirectional uniform wind, comparing the results with those from the GA. RLGA achieves similar results to GA for aligned and staggered layouts and outperforms GA for sunflower and unstructured layouts, demonstrating its efficiency. The sunflower and unstructured layouts' complexity highlights RLGA's robustness and efficiency in tackling complex problems. To further validate its capabilities, we investigate larger wind farms with varying turbine placements ($\Delta x = \Delta y = 5D$ and 2$D$, where $D$ is the wind turbine diameter) under three wind conditions: unidirectional, omnidirectional, and non-uniform, presenting greater challenges. The proposed RLGA is about three times more efficient than GA, especially for complex problems. This improvement stems from RL's ability to adjust parameters, avoiding local optima and accelerating convergence.
We present a large-scale news recommendation system implemented at Ringier Axel Springer Polska, focusing on enhancing prediction models with reinforcement learning techniques. The system, named Aureus, integrates a variety of algorithms, including multi-armed bandit methods and deep learning models based on large language models (LLMs). We detail the architecture and implementation of Aureus, emphasizing the significant improvements in online metrics achieved by combining ranking prediction models with reinforcement learning. The paper further explores the impact of different models mixing on key business performance indicators. Our approach effectively balances the need for personalized recommendations with the ability to adapt to rapidly changing news content, addressing common challenges such as the cold start problem and content freshness. The results of online evaluation demonstrate the effectiveness of the proposed system in a real-world production environment.
Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.
The paper describes LLM unlearning without a retaining dataset, using the ORPO reinforcement learning method with inference enhanced by modified classifier-free guidance. Significant improvement in unlearning, without degradation of the model, is achieved through direct training on synthetic replacement data in CFG-aware training regime, with classifier-free guidance applied during the inference. This article is an extended version of the NeurIPS 2024 LLM-PC submission, which was awarded second prize.
The influence maximization (IM) problem involves identifying a set of key individuals in a social network who can maximize the spread of influence through their network connections. With the advent of geometric deep learning on graphs, great progress has been made towards better solutions for the IM problem. In this paper, we focus on the dynamic non-progressive IM problem, which considers the dynamic nature of real-world social networks and the special case where the influence diffusion is non-progressive, i.e., nodes can be activated multiple times. We first extend an existing diffusion model to capture the non-progressive influence propagation in dynamic social networks. We then propose the method, DNIMRL, which employs deep reinforcement learning and dynamic graph embedding to solve the dynamic non-progressive IM problem. In particular, we propose a novel algorithm that effectively leverages graph embedding to capture the temporal changes of dynamic networks and seamlessly integrates with deep reinforcement learning. The experiments, on different types of real-world social network datasets, demonstrate that our method outperforms state-of-the-art baselines.
Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use Parseval regularization, which maintains orthogonality of weight matrices, to preserve useful optimization properties and improve training in a continual reinforcement learning setting. We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks. We conduct comprehensive ablations to identify the source of its benefits and investigate the effect of certain metrics associated to network trainability including weight matrix rank, weight norms and policy entropy.
In modern chip design, placement aims at placing millions of circuit modules, which is an essential step that significantly influences power, performance, and area (PPA) metrics. Recently, reinforcement learning (RL) has emerged as a promising technique for improving placement quality, especially macro placement. However, current RL-based placement methods suffer from long training times, low generalization ability, and inability to guarantee PPA results. A key issue lies in the problem formulation, i.e., using RL to place from scratch, which results in limits useful information and inaccurate rewards during the training process. In this work, we propose an approach that utilizes RL for the refinement stage, which allows the RL policy to learn how to adjust existing placement layouts, thereby receiving sufficient information for the policy to act and obtain relatively dense and precise rewards. Additionally, we introduce the concept of regularity during training, which is considered an important metric in the chip design industry but is often overlooked in current RL placement methods. We evaluate our approach on the ISPD 2005 and ICCAD 2015 benchmark, comparing the global half-perimeter wirelength and regularity of our proposed method against several competitive approaches. Besides, we test the PPA performance using commercial software, showing that RL as a regulator can achieve significant PPA improvements. Our RL regulator can fine-tune placements from any method and enhance their quality. Our work opens up new possibilities for the application of RL in placement, providing a more effective and efficient approach to optimizing chip design. Our code is available at \url{https://github.com/lamda-bbo/macro-regulator}.
The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-art performance reported in the literature. We currently lack a scalable and widely accepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to hyperparameter tuning for a given set of environments. We then demonstrate the utility of this methodology by assessing the hyperparameter sensitivity of several commonly used normalization variants of PPO. The results suggest that several algorithmic performance improvements may, in fact, be a result of an increased reliance on hyperparameter tuning.
We introduce a new maximum entropy reinforcement learning framework based on the distribution of states and actions visited by a policy. More precisely, an intrinsic reward function is added to the reward function of the Markov decision process that shall be controlled. For each state and action, this intrinsic reward is the relative entropy of the discounted distribution of states and actions (or features from these states and actions) visited during the next time steps. We first prove that an optimal exploration policy, which maximizes the expected discounted sum of intrinsic rewards, is also a policy that maximizes a lower bound on the state-action value function of the decision process under some assumptions. We also prove that the visitation distribution used in the intrinsic reward definition is the fixed point of a contraction operator. Following, we describe how to adapt existing algorithms to learn this fixed point and compute the intrinsic rewards to enhance exploration. A new practical off-policy maximum entropy reinforcement learning algorithm is finally introduced. Empirically, exploration policies have good state-action space coverage, and high-performing control policies are computed efficiently.
The capability of UAVs for efficient autonomous navigation and obstacle avoidance in complex and unknown environments is critical for applications in agricultural irrigation, disaster relief and logistics. In this paper, we propose the DPRL (Distributed Privileged Reinforcement Learning) navigation algorithm, an end-to-end policy designed to address the challenge of high-speed autonomous UAV navigation under partially observable environmental conditions. Our approach combines deep reinforcement learning with privileged learning to overcome the impact of observation data corruption caused by partial observability. We leverage an asymmetric Actor-Critic architecture to provide the agent with privileged information during training, which enhances the model's perceptual capabilities. Additionally, we present a multi-agent exploration strategy across diverse environments to accelerate experience collection, which in turn expedites model convergence. We conducted extensive simulations across various scenarios, benchmarking our DPRL algorithm against the state-of-the-art navigation algorithms. The results consistently demonstrate the superior performance of our algorithm in terms of flight efficiency, robustness and overall success rate.
As natural disasters become increasingly frequent, the need for efficient and equitable evacuation planning has become more critical. This paper proposes a data-driven, reinforcement learning-based framework to optimize bus-based evacuations with an emphasis on improving both efficiency and equity. We model the evacuation problem as a Markov Decision Process solved by reinforcement learning, using real-time transit data from General Transit Feed Specification and transportation networks extracted from OpenStreetMap. The reinforcement learning agent dynamically reroutes buses from their scheduled location to minimize total passengers' evacuation time while prioritizing equity-priority communities. Simulations on the San Francisco Bay Area transportation network indicate that the proposed framework achieves significant improvements in both evacuation efficiency and equitable service distribution compared to traditional rule-based and random strategies. These results highlight the potential of reinforcement learning to enhance system performance and urban resilience during emergency evacuations, offering a scalable solution for real-world applications in intelligent transportation systems.
Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly predictable, but irrelevant to learning a good policy. Such scenarios can lead the model to exhaust its capacity on meaningless content, at the cost of neglecting important environment dynamics. While existing approaches attempt to solve this problem, we highlight its continuing impact on leading MBRL methods -- including DreamerV3 and DreamerPro -- with a novel environment where background distractions are intricate, predictable, and useless for planning future actions. To address this challenge we develop a method for focusing the capacity of the world model through synergy of a pretrained segmentation model, a task-aware reconstruction loss, and adversarial learning. Our method outperforms a variety of other approaches designed to reduce the impact of distractors, and is an advance towards robust model-based reinforcement learning.
The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often lack interpretability and fail to provide clear justifications for their decisions. We propose a method that integrates constraint learning into imitation learning by extracting driving constraints from expert trajectories. Our approach utilizes vectorized scene embeddings that capture critical spatial and temporal features, enabling the model to identify and generalize constraints across various driving scenarios. We formulate the constraint learning problem using a maximum entropy model, which scores the motion planner's trajectories based on their similarity to the expert trajectory. By separating the scoring process into distinct reward and constraint streams, we improve both the interpretability of the planner's behavior and its attention to relevant scene components. Unlike existing constraint learning methods that rely on simulators and are typically embedded in reinforcement learning (RL) or inverse reinforcement learning (IRL) frameworks, our method operates without simulators, making it applicable to a wider range of datasets and real-world scenarios. Experimental results on the InD and TrafficJams datasets demonstrate that incorporating driving constraints enhances model interpretability and improves closed-loop performance.
In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as the limited sample size. Model-based reinforcement learning improves sample efficiency by generating simulated experiences using a learned dynamic model of the environment. However, these synthetic experiences often suffer from the same distribution mismatch. To address these challenges, we introduce SimuDICE, a framework that iteratively refines the initial policy derived from offline data using synthetically generated experiences from the world model. SimuDICE enhances the quality of these simulated experiences by adjusting the sampling probabilities of state-action pairs based on stationary DIstribution Correction Estimation (DICE) and the estimated confidence in the model's predictions. This approach guides policy improvement by balancing experiences similar to those frequently encountered with ones that have a distribution mismatch. Our experiments show that SimuDICE achieves performance comparable to existing algorithms while requiring fewer pre-collected experiences and planning steps, and it remains robust across varying data collection policies.
Deep Reinforcement Learning is gaining increasing attention thanks to its capability to learn complex policies in high-dimensional settings. Recent advancements utilize a dual-network architecture to learn optimal policies through the Q-learning algorithm. However, this approach has notable drawbacks, such as an overestimation bias that can disrupt the learning process and degrade the performance of the resulting policy. To address this, novel algorithms have been developed that mitigate overestimation bias by employing multiple Q-functions. Edge scenarios, which prioritize privacy, have recently gained prominence. In these settings, limited computational resources pose a significant challenge for complex Machine Learning approaches, making the efficiency of algorithms crucial for their performance. In this work, we introduce a novel Reinforcement Learning algorithm tailored for edge scenarios, called Edge Delayed Deep Deterministic Policy Gradient (EdgeD3). EdgeD3 enhances the Deep Deterministic Policy Gradient (DDPG) algorithm, achieving significantly improved performance with $25\%$ less Graphics Process Unit (GPU) time while maintaining the same memory usage. Additionally, EdgeD3 consistently matches or surpasses the performance of state-of-the-art methods across various benchmarks, all while using $30\%$ fewer computational resources and requiring $30\%$ less memory.
Learning from Demonstration (LfD) aims to facilitate rapid Reinforcement Learning (RL) by leveraging expert demonstrations to pre-train the RL agent. However, the limited availability of expert demonstration data often hinders its ability to effectively aid downstream RL learning. To address this problem, we propose a novel two-stage method dubbed as Skill-enhanced Reinforcement Learning Acceleration (SeRLA). SeRLA introduces a skill-level adversarial Positive-Unlabeled (PU) learning model to extract useful skill prior knowledge by enabling learning from both limited expert data and general low-cost demonstration data in the offline prior learning stage. Subsequently, it deploys a skill-based soft actor-critic algorithm to leverage this acquired prior knowledge in the downstream online RL stage for efficient training of a skill policy network. Moreover, we develop a simple skill-level data enhancement technique to further alleviate data sparsity and improve both skill prior learning and downstream skill policy training. Our experimental results on multiple standard RL environments show the proposed SeRLA method achieves state-of-the-art performance on accelerating reinforcement learning on downstream tasks, especially in the early learning phase.
In previous research, we developed methods to train decision trees (DT) as agents for reinforcement learning tasks, based on deep reinforcement learning (DRL) networks. The samples from which the DTs are built, use the environment's state as features and the corresponding action as label. To solve the nontrivial task of selecting samples, which on one hand reflect the DRL agent's capabilities of choosing the right action but on the other hand also cover enough state space to generalize well, we developed an algorithm to iteratively train DTs. In this short paper, we apply this algorithm to a real-world implementation of a robotic task for the first time. Real-world tasks pose additional challenges compared to simulations, such as noise and delays. The task consists of a physical pendulum attached to a cart, which moves on a linear track. By movements to the left and to the right, the pendulum is to be swung in the upright position and balanced in the unstable equilibrium. Our results demonstrate the applicability of the algorithm to real-world tasks by generating a DT whose performance matches the performance of the DRL agent, while consisting of fewer parameters. This research could be a starting point for distilling DTs from DRL agents to obtain transparent, lightweight models for real-world reinforcement learning tasks.
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.