This paper explores the integration of ring attractors, a mathematical model inspired by neural circuit dynamics, into the reinforcement learning (RL) action selection process. Ring attractors, as specialized brain-inspired structures that encode spatial information and uncertainty, offer a biologically plausible mechanism to improve learning speed and predictive performance. They do so by explicitly encoding the action space, facilitating the organization of neural activity, and enabling the distribution of spatial representations across the neural network in the context of deep RL. The application of ring attractors in the RL action selection process involves mapping actions to specific locations on the ring and decoding the selected action based on neural activity. We investigate the application of ring attractors by both building them as exogenous models and integrating them as part of a Deep Learning policy algorithm. Our results show a significant improvement in state-of-the-art models for the Atari 100k benchmark. Notably, our integrated approach improves the performance of state-of-the-art models by half, representing a 53% increase over selected baselines. This paper addresses the challenge of efficient action selection in reinforcement learning (RL), particularly in environments with spatial structures. Our primary contribution is the novel integration of ring attractors (Kim et al., 2017), a neural circuit model from neuroscience, into the RL framework. This approach improves spatial awareness in action selection and provides a mechanism for uncertainty-aware decision making in RL, leading to more accurate and efficient learning in complex environments.

Monte Carlo Exploring Starts (MCES), which aims to learn the optimal policy using only sample returns, is a simple and natural algorithm in reinforcement learning which has been shown to converge under various conditions. However, the convergence rate analysis for MCES-style algorithms in the form of sample complexity has received very little attention. In this paper we develop a finite sample bound for a modified MCES algorithm which solves the stochastic shortest path problem. To this end, we prove a novel result on the convergence rate of the policy iteration algorithm. This result implies that with probability at least $1-\delta$, the algorithm returns an optimal policy after $\tilde{O}(SAK^3\log^3\frac{1}{\delta})$ sampled episodes, where $S$ and $A$ denote the number of states and actions respectively, $K$ is a proxy for episode length, and $\tilde{O}$ hides logarithmic factors and constants depending on the rewards of the environment that are assumed to be known.

In order to train agents that can quickly adapt to new objectives or reward functions, efficient unsupervised representation learning in sequential decision-making environments can be important. Frameworks such as the Exogenous Block Markov Decision Process (Ex-BMDP) have been proposed to formalize this representation-learning problem (Efroni et al., 2022b). In the Ex-BMDP framework, the agent's high-dimensional observations of the environment have two latent factors: a controllable factor, which evolves deterministically within a small state space according to the agent's actions, and an exogenous factor, which represents time-correlated noise, and can be highly complex. The goal of the representation learning problem is to learn an encoder that maps from observations into the controllable latent space, as well as the dynamics of this space. Efroni et al. (2022b) has shown that this is possible with a sample complexity that depends only on the size of the controllable latent space, and not on the size of the noise factor. However, this prior work has focused on the episodic setting, where the controllable latent state resets to a specific start state after a finite horizon. By contrast, if the agent can only interact with the environment in a single continuous trajectory, prior works have not established sample-complexity bounds. We propose STEEL, the first provably sample-efficient algorithm for learning the controllable dynamics of an Ex-BMDP from a single trajectory, in the function approximation setting. STEEL has a sample complexity that depends only on the sizes of the controllable latent space and the encoder function class, and (at worst linearly) on the mixing time of the exogenous noise factor. We prove that STEEL is correct and sample-efficient, and demonstrate STEEL on two toy problems. Code is available at: https://github.com/midi-lab/steel.

Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allowing it to complete new tasks more efficiently. To enable such rapid adaptation to new tasks, we present ReLIC, a new approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention while being trained through self-generated experience via RL. We achieve this by proposing a novel policy update scheme for on-policy RL called "partial updates" as well as a Sink-KV mechanism that enables effective utilization of a long observation history for embodied agents. Our method outperforms a variety of meta-RL baselines in adapting to unseen houses in an embodied multi-object navigation task. In addition, we find that ReLIC is capable of few-shot imitation learning despite never being trained with expert demonstrations. We also provide a comprehensive analysis of ReLIC, highlighting that the combination of large-scale RL training, the proposed partial updates scheme, and the Sink-KV are essential for effective in-context learning. The code for ReLIC and all our experiments is at github.com/aielawady/relic. A desired capability of intelligent embodied agents is to rapidly adapt to new scenarios through experience. An essential requirement for this capability is integrating a long history of experience into decision-making to enable an agent to accumulate knowledge about the new scenario that it is encountering. For example, a robot placed in an unseen house initially has no knowledge of the home layout and where to find objects. The robot should leverage its history of experiences of completing tasks in this new home to learn the home layout details, where to find objects, and how to act to complete tasks successfully. To achieve adaptation of decision-making to new tasks, prior work has leveraged a technique called in-context reinforcement learning (RL) where an agent is trained with RL to utilize past experience in an environment (Wang et al., 2016; Team et al., 2023; Duan et al., 2016; Grigsby et al., 2023; Melo, 2022). By using sequence models over a history of interactions in an environment, these methods adapt to new scenarios by conditioning policy actions on this context of interaction history without updating the policy parameters.

Predictive business process analytics has become important for organizations, offering real-time operational support for their processes. However, these algorithms often perform unfair predictions because they are based on biased variables (e.g., gender or nationality), namely variables embodying discrimination. This paper addresses the challenge of integrating a debiasing phase into predictive business process analytics to ensure that predictions are not influenced by biased variables. Our framework leverages on adversial debiasing is evaluated on four case studies, showing a significant reduction in the contribution of biased variables to the predicted value. The proposed technique is also compared with the state of the art in fairness in process mining, illustrating that our framework allows for a more enhanced level of fairness, while retaining a better prediction quality.

The widely used expected utility theory has been shown to be empirically inconsistent with human preferences in the psychology and behavioral economy literatures. Cumulative Prospect Theory (CPT) has been developed to fill in this gap and provide a better model for human-based decision-making supported by empirical evidence. It allows to express a wide range of attitudes and perceptions towards risk, gains and losses. A few years ago, CPT has been combined with Reinforcement Learning (RL) to formulate a CPT policy optimization problem where the goal of the agent is to search for a policy generating long-term returns which are aligned with their preferences. In this work, we revisit this policy optimization problem and provide new insights on optimal policies and their nature depending on the utility function under consideration. We further derive a novel policy gradient theorem for the CPT policy optimization objective generalizing the seminal corresponding result in standard RL. This result enables us to design a model-free policy gradient algorithm to solve the CPT-RL problem. We illustrate the performance of our algorithm in simple examples motivated by traffic control and electricity management applications. We also demonstrate that our policy gradient algorithm scales better to larger state spaces compared to the existing zeroth order algorithm for solving the same problem.

The quality of Machine Learning (ML) models strongly depends on the input data, as such generating high-quality features is often required to improve the predictive accuracy. This process is referred to as Feature Engineering (FE). However, since manual feature engineering is time-consuming and requires case-by-case domain knowledge, Automated Feature Engineering (AutoFE) is crucial. A major challenge that remains is to generate interpretable features. To tackle this problem, we introduce SMART, a hybrid approach that uses semantic technologies to guide the generation of interpretable features through a two-step process: Exploitation and Exploration. The former uses Description Logics (DL) to reason on the semantics embedded in Knowledge Graphs (KG) to infer domain-specific features, while the latter exploits the knowledge graph to conduct a guided exploration of the search space through Deep Reinforcement Learning (DRL). Our experiments on public datasets demonstrate that SMART significantly improves prediction accuracy while ensuring a high level of interpretability.

With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing novelty, diversity, or uncertainty attracts increasing attention, redundant efforts brought by exploration without proper guidance choices poses a practical issue for the community. This paper introduces a systematic approach, termed LEMAE, choosing to channel informative task-relevant guidance from a knowledgeable Large Language Model (LLM) for Efficient Multi-Agent Exploration. Specifically, we ground linguistic knowledge from LLM into symbolic key states, that are critical for task fulfillment, in a discriminative manner at low LLM inference costs. To unleash the power of key states, we design Subspace-based Hindsight Intrinsic Reward (SHIR) to guide agents toward key states by increasing reward density. Additionally, we build the Key State Memory Tree (KSMT) to track transitions between key states in a specific task for organized exploration. Benefiting from diminishing redundant explorations, LEMAE outperforms existing SOTA approaches on the challenging benchmarks (e.g., SMAC and MPE) by a large margin, achieving a 10x acceleration in certain scenarios.

E FFICIENT R ESIDUAL L EARNING WITH M IXTURE-OF-E XPERTS FOR U NIVERSAL D EXTEROUSG RASPING Ziye Huang 1, Haoqi Y uan 1, Y uhui Fu 1, Zongqing Lu 1,2 1 Peking University 2 Beijing Academy of Artificial Intelligence A BSTRACT Universal dexterous grasping across diverse objects presents a fundamental yet formidable challenge in robot learning. Existing approaches using reinforcement learning (RL) to develop policies on extensive object datasets face critical limitations, including complex curriculum design for multi-task learning and limited generalization to unseen objects. To overcome these challenges, we introduce ResDex, a novel approach that integrates residual policy learning with a mixture-of-experts (MoE) framework. ResDex is distinguished by its use of geometry-unaware base policies that are efficiently acquired on individual objects and capable of generalizing across a wide range of unseen objects. Our MoE framework incorporates several base policies to facilitate diverse grasping styles suitable for various objects. By learning residual actions alongside weights that combine these base policies, ResDex enables efficient multi-task RL for universal dexterous grasping. ResDex achieves state-of-the-art performance on the DexGraspNet dataset comprising 3,200 objects with an 88.8% success rate. It exhibits no generalization gap with unseen objects and demonstrates superior training efficiency, mastering all tasks within only 12 hours on a single GPU. 1 I NTRODUCTION Dexterous robotic hands (Pons et al., 1999; Shaw et al., 2023) provide advanced capabilities for complex grasping tasks, similar to those performed by human hands. However, achieving universal dexterous grasping across a wide range of objects remains a significant challenge due to the high degrees of freedom (DoFs) for dexterous hands and the high variability in object geometry in the real world. Previous works (Qin et al., 2022a; Agarwal et al., 2023) develop dexterous grasping policies using reinforcement learning (RL), but these policies are limited to a small range of objects that are similar to the training objects.

Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning under temporally extended objectives in a receding horizon manner. To this end, we propose DOPPLER, a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL). Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. It leverages diffusion models to generate options with low-level actions. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options, leading to more efficient querying. Experiments on robot navigation and manipulation tasks demonstrate that DOPPLER can generate sequences of trajectories that progressively satisfy the specified formulae for obstacle avoidance and sequential visitation. Demonstration videos are available online at: https://philiptheother.github.io/doppler/.