搜索结果：Reinforcement

Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional. In this work, we present a simple yet effective representation-level prior that inserts a fixed orthonormal projection to constrain encoder features to a low-dimensional subspace, requiring no auxiliary objectives, pretraining, or changes to the underlying RL algorithm. Under a linear realizability assumption, we prove that when the bottleneck dimension exceeds the intrinsic rank of the optimal value function in feature space, the bottleneck preserves expressivity and leaves the induced gradient dynamics unchanged up to an equivalent low-dimensional parameterization. Empirically, we find that across both single and multi-task benchmarks, baseline performance is either matched or improved once the bottleneck dimension exceeds a small task-dependent threshold; in many cases, value representations can be compressed to extremely low dimensions without loss, and the minimal sufficient dimension depends far more on environment complexity than encoder width. In addition, we analyze rep

Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value bonus can be learned by estimating a value function on reward bonuses, propagating local uncertainties around rewards. However, this approach only increases the value bonus for an action retroactively, after seeing a higher reward bonus from that state and action. Such an approach does not encourage the agent to visit a state and action for the first time. In this work, we introduce an algorithm for exploration called Value Bonuses with Ensemble errors (VBE), that maintains an ensemble of random action-value functions (RQFs). VBE uses the errors in the estimation of these RQFs to design value bonuses that provide first-visit optimism and deep exploration. The key idea is to design the rewards for these RQFs in such a way that the value bonus can decrease to zero. We show that VBE outperforms Bootstrap DQN and two reward bonus approaches (RND and ACB) on several classic environments used to test exploration and provide demonstrative experiments that it can scale eas

In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the original dataset making it usable for training the policy. In contrast to other approaches, our method does not require optimal trajectories. Through experiments on the D4RL benchmark we demonstrate that TROFI consistently outperforms baselines and performs comparably to using the ground truth reward to learn policies. Additionally, we validate the efficacy of our method in a 3D game environment. Our studies of the reward model highlight the importance of the reward function in this setting: we show that to ensure the alignment of a value function to the actual future discounted reward, it is fundame

The increasing complexity of Intelligent Transportation Systems (ITS) has led to significant interest in computational offloading to external infrastructures such as edge servers, vehicular nodes, and UAVs. These dynamic and heterogeneous environments pose challenges for traditional offloading strategies, prompting the exploration of Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) as adaptive decision-making frameworks. This survey presents a comprehensive review of recent advances in DRL-based offloading for vehicular edge computing (VEC). We classify and compare existing works based on learning paradigms (e.g., single-agent, multi-agent), system architectures (e.g., centralized, distributed, hierarchical), and optimization objectives (e.g., latency, energy, fairness). Furthermore, we analyze how Markov Decision Process (MDP) formulations are applied and highlight emerging trends in reward design, coordination mechanisms, and scalability. Finally, we identify open challenges and outline future research directions to guide the development of robust and intelligent offloading strategies for next-generation ITS.

This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning. Different from the existing preference-based and ranking-based reinforcement learning paradigms, based on human relative preferences over sample pairs, the proposed rating-based reinforcement learning approach is based on human evaluation of individual trajectories without relative comparisons between sample pairs. The rating-based reinforcement learning approach builds on a new prediction model for human ratings and a novel multi-class loss function. We conduct several experimental studies based on synthetic ratings and real human ratings to evaluate the effectiveness and benefits of the new rating-based reinforcement learning approach.

Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.

Designing effective task sequences is crucial for curriculum reinforcement learning (CRL), where agents must gradually acquire skills by training on intermediate tasks. A key challenge in CRL is to identify tasks that promote exploration, yet are similar enough to support effective transfer. While recent approach suggests comparing tasks via their Structural Causal Models (SCMs), the method requires access to ground-truth causal structures, an unrealistic assumption in most RL settings. In this work, we propose Causal-Paced Deep Reinforcement Learning (CP-DRL), a curriculum learning framework aware of SCM differences between tasks based on interaction data approximation. This signal captures task novelty, which we combine with the agent's learnability, measured by reward gain, to form a unified objective. Empirically, CP-DRL outperforms existing curriculum methods on the Point Mass benchmark, achieving faster convergence and higher returns. CP-DRL demonstrates reduced variance with comparable final returns in the Bipedal Walker-Trivial setting, and achieves the highest average performance in the Infeasible variant. These results indicate that leveraging causal relationships between

As image-based deep reinforcement learning tackles more challenging tasks, increasing model size has become an important factor in improving performance. Recent studies achieved this by focusing on the parameter efficiency of scaled networks, typically using Impala-CNN, a 15-layer ResNet-inspired network, as the image encoder. However, while Impala-CNN evidently outperforms older CNN architectures, potential advancements in network design for deep reinforcement learning-specific image encoders remain largely unexplored. We find that replacing the flattening of output feature maps in Impala-CNN with global average pooling leads to a notable performance improvement. This approach outperforms larger and more complex models in the Procgen Benchmark, particularly in terms of generalization. We call our proposed encoder model Impoola-CNN. A decrease in the network's translation sensitivity may be central to this improvement, as we observe the most significant gains in games without agent-centered observations. Our results demonstrate that network scaling is not just about increasing model size - efficient network design is also an essential factor. We make our code available at https://g

Large language models (LLMs) trained with reinforcement objectives often achieve superficially correct answers via shortcut strategies, pairing correct outputs with spurious or unfaithful reasoning and degrading under small causal perturbations. We introduce Causally-Enhanced Policy Optimization (CE-PO), a drop-in reward-shaping framework that augments policy optimization with a differentiable proxy for causal coherence along the generation pathway from prompt (Z) to rationale (X) to answer (Y). CE-PO estimates model-internal influence with Jacobian-based sensitivities, counterfactually hardens these signals to suppress nuisance cues, and fuses the resulting coherence score with task-accuracy feedback via a Minkowski (power-mean) combiner, exposing a single tunable between accuracy and coherence trade-off. The unified reward integrates with PPO/GRPO without architectural changes. Across reasoning benchmarks and causal stress tests, CE-PO reduces reward hacking and unfaithful chain-of-thought while improving robustness to correlation-causation flips and light counterfactual edits, all at near-parity accuracy. Experimental results across 4 datasets show that CE-PO improves accuracy o

Recent work has shown that, under certain assumptions, zero-shot reinforcement learning (RL) methods can generalise to any unseen task in an environment after reward-free pre-training. Access to Markov states is one such assumption, yet, in many real-world applications, the Markov state is only partially observable. Here, we explore how the performance of standard zero-shot RL methods degrades when subjected to partially observability, and show that, as in single-task RL, memory-based architectures are an effective remedy. We evaluate our memory-based zero-shot RL methods in domains where the states, rewards and a change in dynamics are partially observed, and show improved performance over memory-free baselines. Our code is open-sourced via: https://enjeeneer.io/projects/bfms-with-memory/.

Within wind farms, wake effects between turbines can significantly reduce overall energy production. Wind farm flow control encompasses methods designed to mitigate these effects through coordinated turbine control. Wake steering, for example, consists in intentionally misaligning certain turbines with the wind to optimize airflow and increase power output. However, designing a robust wake steering controller remains challenging, and existing machine learning approaches are limited to quasi-static wind conditions or small wind farms. This work presents a new deep reinforcement learning methodology to develop a wake steering policy that overcomes these limitations. Our approach introduces a novel architecture that combines graph attention networks and multi-head self-attention blocks, alongside a novel reward function and training strategy. The resulting model computes the yaw angles of each turbine, optimizing energy production in time-varying wind conditions. An empirical study conducted on steady-state, low-fidelity simulation, shows that our model requires approximately 10 times fewer training steps than a fully connected neural network and achieves more robust performance compa

When using reinforcement learning (RL) to tackle physical control tasks, inductive biases that encode physics priors can help improve sample efficiency during training and enhance generalization in testing. However, the current practice of incorporating these helpful physics-informed inductive biases inevitably runs into significant manual labor and domain expertise, making them prohibitive for general users. This work explores a symbolic approach to distill physics-informed inductive biases into RL agents, where the physics priors are expressed in a domain-specific language (DSL) that is human-readable and naturally explainable. Yet, the DSL priors do not translate directly into an implementable policy due to partial and noisy observations and additional physical constraints in navigation tasks. To address this gap, we develop a physics-informed program-guided RL (PiPRL) framework with applications to indoor navigation. PiPRL adopts a hierarchical and modularized neuro-symbolic integration, where a meta symbolic program receives semantically meaningful features from a neural perception module, which form the bases for symbolic programming that encodes physics priors and guides the

The research field of automated negotiation has a long history of designing agents that can negotiate with other agents. Such negotiation strategies are traditionally based on manual design and heuristics. More recently, reinforcement learning approaches have also been used to train agents to negotiate. However, negotiation problems are diverse, causing observation and action dimensions to change, which cannot be handled by default linear policy networks. Previous work on this topic has circumvented this issue either by fixing the negotiation problem, causing policies to be non-transferable between negotiation problems or by abstracting the observations and actions into fixed-size representations, causing loss of information and expressiveness due to feature design. We developed an end-to-end reinforcement learning method for diverse negotiation problems by representing observations and actions as a graph and applying graph neural networks in the policy. With empirical evaluations, we show that our method is effective and that we can learn to negotiate with other agents on never-before-seen negotiation problems. Our result opens up new opportunities for reinforcement learning in ne

Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain preferences, this approach cannot capture fairness-oriented goals such as Nash social welfare or max-min fairness, which require nonlinear and non-additive trade-offs. Although several online algorithms have been proposed for specific fairness objectives, a unified approach for optimizing nonlinear welfare criteria in the offline setting-where learning must proceed from a fixed dataset-remains unexplored. In this work, we present FairDICE, the first offline MORL framework that directly optimizes nonlinear welfare objective. FairDICE leverages distribution correction estimation to jointly account for welfare maximization and distributional regularization, enabling stable and sample-efficient learning without requiring explicit preference weights or exhaustive weight search. Across multiple offline benchmarks, FairDICE demonstrates strong fairness-aware performance compared to existing baselines.

Since deep neural networks' resurgence, reinforcement learning has gradually strengthened and surpassed humans in many conventional games. However, it is not easy to copy these accomplishments to autonomous driving because state spaces are immensely complicated in the real world and action spaces are continuous and fine control is necessary. Besides, autonomous driving systems must also maintain their functionality regardless of the environment's complexity. The deep reinforcement learning domain (DRL) has become a robust learning framework to handle complex policies in high dimensional surroundings with deep representation learning. This research outlines deep, reinforcement learning algorithms (DRL). It presents a nomenclature of autonomous driving in which DRL techniques have been used, thus discussing important computational issues in evaluating autonomous driving agents in the real environment. Instead, it involves similar but not standard RL techniques, adjoining fields such as emulation of actions, modelling imitation, inverse reinforcement learning. The simulators' role in training agents is addressed, as are the methods for validating, checking and robustness of existing R

Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with the majority of RL-based efforts having been allocated to discounted MDPs. In this work, we study a unique structural property of average-reward MDPs and utilize it to introduce Reward-Extended Differential (or RED) reinforcement learning: a novel RL framework that can be used to effectively and efficiently solve various learning objectives, or subtasks, simultaneously in the average-reward setting. We introduce a family of RED learning algorithms for prediction and control, including proven-convergent algorithms for the tabular case. We then showcase the power of these algorithms by demonstrating how they can be used to learn a policy that optimizes, for the first time, the well-known conditional value-at-risk (CVaR) risk measure in a fully-online manner, without the use of an explicit bi-level optimization scheme or an augmented state-space.

In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user instructions, and bolstering inferential strength. Although existing surveys offer overviews of RL augmented LLMs, their scope is often limited, failing to provide a comprehensive summary of how RL operates across the full lifecycle of LLMs. We systematically review the theoretical and practical advancements whereby RL empowers LLMs, especially Reinforcement Learning with Verifiable Rewards (RLVR). First, we briefly introduce the basic theory of RL. Second, we thoroughly detail application strategies for RL across various phases of the LLM lifecycle, including pre-training, alignment fine-tuning, and reinforced reasoning. In particular, we emphasize that RL methods in the reinforced reasoning phase serve as a pivotal driving force for advancing model reasoning to its limits. Next, we collate existing datasets and evaluation benchmarks currently used for RL fine-tuning, spanning human-annotated datasets, AI-assisted preference data, and program-verification

Quantum computing offers exciting opportunities for simulating complex quantum systems and optimizing large scale combinatorial problems, but its practical use is limited by device noise and constrained connectivity. Designing quantum circuits, which are fundamental to quantum algorithms, is therefore a central challenge in current quantum hardware. Existing reinforcement learning based methods for circuit design lose accuracy when restricted to hardware native gates and device level compilation. Here, we introduce gadget reinforcement learning (GRL), which combines learning with program synthesis to automatically construct composite gates that expand the action space while respecting hardware constraints. We show that this approach improves accuracy, hardware compatibility, and scalability for transverse-field Ising and quantum chemistry problems, reaching systems of up to ten qubits within realistic computational budgets. This framework demonstrates how learned, reusable circuit building blocks can guide the co-design of algorithms and hardware for quantum processors.

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However, neither method alone results in an agent that will consistently learn intelligent behavior across environments. In an effort to find a single entropy-based method that will encourage emergent behaviors in any environment, we propose an agent that can adapt its objective online, depending on the entropy conditions by framing the choice as a multi-armed bandit problem. We devise a novel intrinsic feedback signal for the bandit, which captures the agent's ability to control the entropy in its environment. We demonstrate that such agents can learn to control entropy and exhibit emergent behaviors in both high- and low-entropy regimes and can learn skillful behaviors in benchmark tasks. Videos of the trained agents and summarized findings can be found on our project page https://sites.google.com/view/surprise-adaptive-agents