In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dynamics. We propose a novel approach, Trajectory Encoding Augmentation (TEA), which extends the state space by integrating latent representations of environmental dynamics obtained from sequence encoders, such as AutoEncoders. Our findings show that incorporating these encodings with TEA improves the transferability of a single policy to novel environments with new dynamics, surpassing methods that rely solely on unmodified states. These results indicate that TEA captures critical, environment-specific characteristics, enabling RL agents to generalize effectively across dynamic conditions.

Forecasting irregular time series presents significant challenges due to two key issues: the vulnerability of models to mean regression, driven by the noisy and complex nature of the data, and the limitations of traditional error-based evaluation metrics, which fail to capture meaningful patterns and penalize unrealistic forecasts. These problems result in forecasts which are often misaligned with human intuition. To tackle these challenges, we propose an adversarial learning framework with a deep analysis of adversarial components. Specifically, we emphasize the importance of balancing the modeling of global distribution (overall patterns) and transition dynamics (localized temporal changes) to better capture the nuances of irregular time series. Overall, this research provides practical insights for improving models and evaluation metrics, and pioneers the application of adversarial learning in the domain of irregular time-series forecasting.

Reinforcement Learning (RL) has emerged as a powerful paradigm in Artificial Intelligence (AI), enabling agents to learn optimal behaviors through interactions with their environments. Drawing from the foundations of trial and error, RL equips agents to make informed decisions through feedback in the form of rewards or penalties. This paper presents a comprehensive survey of RL, meticulously analyzing a wide range of algorithms, from foundational tabular methods to advanced Deep Reinforcement Learning (DRL) techniques. We categorize and evaluate these algorithms based on key criteria such as scalability, sample efficiency, and suitability. We compare the methods in the form of their strengths and weaknesses in diverse settings. Additionally, we offer practical insights into the selection and implementation of RL algorithms, addressing common challenges like convergence, stability, and the exploration-exploitation dilemma. This paper serves as a comprehensive reference for researchers and practitioners aiming to harness the full potential of RL in solving complex, real-world problems.

Reinforcement Learning (RL) has been widely applied in recommendation systems to capture users' long-term engagement, thereby improving dwelling time and enhancing user retention. In the context of a short video & live-stream mixed recommendation scenario, the live-stream recommendation system (RS) decides whether to inject at most one live-stream into the video feed for each user request. To maximize long-term user engagement, it is crucial to determine an optimal live-stream injection policy for accurate live-stream allocation. However, traditional RL algorithms often face divergence and instability problems, and these issues are even more pronounced in our scenario. To address these challenges, we propose a novel Supervised Learning-enhanced Multi-Group Actor Critic algorithm (SL-MGAC). Specifically, we introduce a supervised learning-enhanced actor-critic framework that incorporates variance reduction techniques, where multi-task reward learning helps restrict bootstrapping error accumulation during critic learning. Additionally, we design a multi-group state decomposition module for both actor and critic networks to reduce prediction variance and improve model stability. Empirically, we evaluate the SL-MGAC algorithm using offline policy evaluation (OPE) and online A/B testing. Experimental results demonstrate that the proposed method not only outperforms baseline methods but also exhibits enhanced stability in online recommendation scenarios.

Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgraph Bellman operators, that interpolate between bootstrapping and rollout methods. Our estimator, derived by solving the fixed point of the empirical subgraph Bellman operator, combines the strengths of the bootstrapping-based temporal difference (TD) estimator and the rollout-based Monte Carlo (MC) methods. Specifically, the error upper bound of our estimator approaches the optimal variance achieved by TD, with an additional term depending on the exit probability of a selected subset of the state space. At the same time, the estimator exhibits the finite-sample adaptivity of MC, with sample complexity depending only on the occupancy measure of this subset. We complement the upper bound with an information-theoretic lower bound, showing that the additional term is unavoidable given a reasonable sample size. Together, these results establish subgraph Bellman estimators as an optimal and adaptive framework for reconciling TD and MC methods in policy evaluation.

We initiate a study of the geometry of the visual representation space -- the information channel from the vision encoder to the action decoder -- in an image-based control pipeline learned from behavior cloning. Inspired by the phenomenon of neural collapse (NC) in image classification (arXiv:2008.08186), we empirically demonstrate the prevalent emergence of a similar law of clustering in the visual representation space. Specifically, in discrete image-based control (e.g., Lunar Lander), the visual representations cluster according to the natural discrete action labels; in continuous image-based control (e.g., Planar Pushing and Block Stacking), the clustering emerges according to "control-oriented" classes that are based on (a) the relative pose between the object and the target in the input or (b) the relative pose of the object induced by expert actions in the output. Each of the classes corresponds to one relative pose orthant (REPO). Beyond empirical observation, we show such a law of clustering can be leveraged as an algorithmic tool to improve test-time performance when training a policy with limited expert demonstrations. Particularly, we pretrain the vision encoder using NC as a regularization to encourage control-oriented clustering of the visual features. Surprisingly, such an NC-pretrained vision encoder, when finetuned end-to-end with the action decoder, boosts the test-time performance by 10% to 35%. Real-world vision-based planar pushing experiments confirmed the surprising advantage of control-oriented visual representation pretraining.

Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number of statistics from the datasets and then use machine-learning models to score or classify multiple visualizations choices to recommend the most effective ones, as per the statistics. However, state-of-the art models rely on very large number of expensive statistics and therefore using such models on large datasets become infeasible due to prohibitively large computational time, limiting the effectiveness of such techniques to most real world complex and large datasets. In this paper, we propose a novel reinforcement-learning (RL) based framework that takes a given vis-rec model and a time-budget from the user and identifies the best set of input statistics that would be most effective while generating the visual insights within a given time budget, using the given model. Using two state-of-the-art vis-rec models applied on three large real-world datasets, we show the effectiveness of our technique in significantly reducing time-to visualize with very small amount of introduced error. Our approach is about 10X times faster compared to the baseline approaches that introduce similar amounts of error.

As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions that deviate significantly from prior experiences, explore the world safely, understand pragmatics, and can cooperate to meet their intrinsic goals. Intelligence, when coupled with cooperation and safety mechanisms, can drive sustained progress and well-being. These properties are a function of the architecture of the brain and the learning algorithms it implements. Neuroscience may thus hold important keys to technical AI safety that are currently underexplored and underutilized. In this roadmap, we highlight and critically evaluate several paths toward AI safety inspired by neuroscience: emulating the brain's representations, information processing, and architecture; building robust sensory and motor systems from imitating brain data and bodies; fine-tuning AI systems on brain data; advancing interpretability using neuroscience methods; and scaling up cognitively-inspired architectures. We make several concrete recommendations for how neuroscience can positively impact AI safety.

Wastewater treatment plants face unique challenges for process control due to their complex dynamics, slow time constants, and stochastic delays in observations and actions. These characteristics make conventional control methods, such as Proportional-Integral-Derivative controllers, suboptimal for achieving efficient phosphorus removal, a critical component of wastewater treatment to ensure environmental sustainability. This study addresses these challenges using a novel deep reinforcement learning approach based on the Soft Actor-Critic algorithm, integrated with a custom simulator designed to model the delayed feedback inherent in wastewater treatment plants. The simulator incorporates Long Short-Term Memory networks for accurate multi-step state predictions, enabling realistic training scenarios. To account for the stochastic nature of delays, agents were trained under three delay scenarios: no delay, constant delay, and random delay. The results demonstrate that incorporating random delays into the reinforcement learning framework significantly improves phosphorus removal efficiency while reducing operational costs. Specifically, the delay-aware agent achieved 36% reduction in phosphorus emissions, 55% higher reward, 77% lower target deviation from the regulatory limit, and 9% lower total costs than traditional control methods in the simulated environment. These findings underscore the potential of reinforcement learning to overcome the limitations of conventional control strategies in wastewater treatment, providing an adaptive and cost-effective solution for phosphorus removal.

This paper explores the application of a reinforcement learning (RL) framework using the Q-Learning algorithm to enhance dynamic pricing strategies in the retail sector. Unlike traditional pricing methods, which often rely on static demand models, our RL approach continuously adapts to evolving market dynamics, offering a more flexible and responsive pricing strategy. By creating a simulated retail environment, we demonstrate how RL effectively addresses real-time changes in consumer behavior and market conditions, leading to improved revenue outcomes. Our results illustrate that the RL model not only surpasses traditional methods in terms of revenue generation but also provides insights into the complex interplay of price elasticity and consumer demand. This research underlines the significant potential of applying artificial intelligence in economic decision-making, paving the way for more sophisticated, data-driven pricing models in various commercial domains.