Model-based planning holds great promise for improving both sample efficiency and generalization in reinforcement learning (RL). We show that energy-based models (EBMs) are a promising class of models to use for model-based planning. EBMs naturally support inference of intermediate states given start and goal state dis…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “online planning”
Paper tackles continual reinforcement learning by forgetting, proposing a planning method with online world models.
problem Catastrophic forgetting in reinforcement learning when learning new tasks.
method Planning with an online world model using model predictive control.
result The proposed FTL Online Agent (OA) learns new tasks without forgetting old skills.
New framework guides resource usage to achieve sublinear regret in adversarial settings.
problem Achieving sublinear regret in online decision making with changing reward and cost distributions.
method General primal-dual methods guided by spending plans that ensure balanced resource usage.
result Achieves sublinear regret with respect to spending plans that balance resource usage.
We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning methods have achieved successes in difficult tasks due to their broad flexibility, …
Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…
New method optimizes experiments under constraints.
problem Adapting BED to dynamic constraints in real-world tasks.
method Offline pre-training of an amortized policy and posterior network with online multi-step lookahead planning.
result Significantly more informative design sequences than existing methods.
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…
In this paper, we present a new task that investigates how people interact with and make judgments about towers of blocks. In Experiment~1, participants in the lab solved a series of problems in which they had to re-configure three blocks from an initial to a final configuration. We recorded whether they used one hand …
We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and…
New policy for non-stationary multi-armed bandits with recovering rewards.
problem Non-stationary multi-armed bandits with recovering rewards.
method Purely Periodic Policies integrating upper confidence bound procedure.
result Approximately regret against the offline benchmark.
A big challenge in environmental monitoring is the spatiotemporal variation of the phenomena to be observed. To enable persistent sensing and estimation in such a setting, it is beneficial to have a time-varying underlying environmental model. Here we present a planning and learning method that enables an autonomous ma…
Maximize to Explore integrates RL components for efficient policy discovery.
problem Balancing exploration and exploitation in online RL with general function approximators.
method Integrates estimation, planning, and exploration into a single objective function.
result Achieves sublinear regret for MDPs and MGs with general function approximations.
Real Time Dynamic Programming (RTDP) is an online algorithm based on Dynamic Programming (DP) that acts by 1-step greedy planning. Unlike DP, RTDP does not require access to the entire state space, i.e., it explicitly handles the exploration. This fact makes RTDP particularly appealing when the state space is large and…
Accurate MR-to-CT synthesis is a requirement for MR-only workflows in radiotherapy (RT) treatment planning. In recent years, deep learning-based approaches have shown impressive results in this field. However, to prevent downstream errors in RT treatment planning, it is important that deep learning models are only appl…
We propose a meta path planning algorithm named \emph{Neural Exploration-Exploitation Trees~(NEXT)} for learning from prior experience for solving new path planning problems in high dimensional continuous state and action spaces. Compared to more classical sampling-based methods like RRT, our approach achieves much bet…
PDSketch enables flexible robot planning by learning from domain structures.
problem Building general robots with flexible planning.
method Exploiting locality and sparsity in environmental models, PDSketch defines high-level structures for trainable neural networks.
result PDSketch automatically generates planning heuristics without additional training.
We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is …
We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local traj…
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
Automated planning is one of the foundational areas of AI. Since no single planner can work well for all tasks and domains, portfolio-based techniques have become increasingly popular in recent years. In particular, deep learning emerges as a promising methodology for online planner selection. Owing to the recent devel…
Model learns and plans in real-time under constraints for robotic systems.
problem Challenges in applying reinforcement learning to robotic systems, especially handling continuous state and action spaces, time/resource budget, and hard constraints.
method Combines Gaussian Process regression and Receding Horizon Control. Uses sparse spectrum Gaussian Processes for incremental model updates from sensory data.
result Demonstrates benefits of online learning on autonomous racing tasks and reusability of learned dynamics.
Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to achieve goals. Yet, reward functions that evoke desirable behavior are often difficul…
Integrates skills and world models for efficient task solving and transfer.
problem Quickly solve new tasks in complex environments using reusable knowledge.
method Leverages partial amortization for fast adaptation and online skill planning.
result Improved sample efficiency in single tasks and transfer between tasks.
A new algorithm learns optimal personalized treatment plans online with low regret.
problem Learning optimal dynamic treatment regimes in an online setting.
method Developed a novel algorithm balancing exploration and exploitation for rate-optimal regret.
result Guaranteed rate-optimal regret for linear transition and reward models.
We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance relative to the Bayes optimal policy, with a lower computational complexity. Th…
Paper proposes methods to help autonomous vehicles adapt to unexpected driving scenarios.
problem Autonomous vehicles struggle with unexpected driving conditions.
method Robust imitative planning (RIP) and adaptive robust imitative planning (AdaRIP) methods to detect and adapt to distribution shifts.
result Methods outperform current state-of-the-art approaches in nuScenes prediction challenge.
In an online contract selection problem there is a seller which offers a set of contracts to sequentially arriving buyers whose types are drawn from an unknown distribution. If there exists a profitable contract for the buyer in the offered set, i.e., a contract with payoff higher than the payoff of not accepting any c…
New online method estimates OT distances from sample streams.
problem Computing OT distances between arbitrary distributions.
method Online Sinkhorn algorithm using iterative enrichment of non-parametric representation.
result Consistent estimation of true regularized OT distance with nearly-O(1/n) sample complexity.
New method for predicting paths of unpredictable objects with high confidence.
problem Need for dependable uncertainty estimates in motion planning with diverse unpredictable objects.
method Blend online conformal prediction, multiple time series techniques, and heteroscedasticity addressing.
result Simultaneous forecasting bands that cover entire paths with high probability.
Paper proposes online learning for estimating AC network admittance matrix.
problem Missing or outdated information on power grid topology and parameters.
method Recursive identification algorithm using phasor measurements, enhanced with DOE for optimal data excitation.
result Improves on existing techniques and substantiated by numerical studies.
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
New model for personalized online advertising with multi-user interaction.
problem Realistic online advertising scenarios with multiple users interacting simultaneously.
method Introduces Multi-User Contextual Cascading Bandit (MCCB) model and proposes UCBBP and AUCBBP algorithms.
result Proves UCBBP and AUCBBP achieve optimal regret bounds for multi-user context.
The paper tackles robust design selection for online experiments under uncertain interference mechanisms.
problem Designing experiments in ads, recommendations, and member-experience systems when interference mechanisms are unknown.
method Formulates the problem as robust design selection over uncertain exposure mechanisms. Compares designs by worst-case planning risk over an ambiguity set combining various factors.
result Develops a geometry-aware guarantee and robust selector theorem with excess-risk control, exact recovery under separation, and certified shortlists when the risk surface is flat.
Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the va…
New algorithm reduces regret in online learning for piecewise continuous functions.
problem Exponential loss in efficiency when moving from classical to adversarial learning.
method Introduces generalized bracketing numbers and Follow-the-Perturbed-Leader algorithm.
result Optimal scaling of optimization oracle calls with average regret.
Cultural activity is an inherent aspect of urban life and the success of a modern city is largely determined by its capacity to offer generous cultural entertainment to its citizens. To this end, the optimal allocation of cultural establishments and related resources across urban regions becomes of vital importance, as…
A new algorithm reduces memory usage for deep learning models.
problem Training deep learning models requires significant memory.
method Dynamic Tensor Rematerialization (DTR) is a greedy online algorithm that dynamically plans recomputations.
result DTR achieves comparable performance to optimal static checkpointing with only a small memory budget.
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors. The classic challenges in the information acquisition prob…
New clustering method uses Wasserstein distance to analyze simulation outputs.
problem Analyzing stochastic simulation outputs to uncover relationships and patterns.
method Agglomerative clustering using regularized Wasserstein distance.
result Identifies staffing plans yielding similar performance outcomes.
MEGAN models chemical reactions as graph edits, improving synthesis planning.
problem Generating and predicting chemical reactions under constraints.
method End-to-end encoder-decoder neural model inspired by arrow pushing formalism.
result State-of-the-art accuracy in standard benchmarks for retrosynthesis prediction.
Interpersonal relations are fickle, with close friendships often dissolving into enmity. In this work, we explore linguistic cues that presage such transitions by studying dyadic interactions in an online strategy game where players form alliances and break those alliances through betrayal. We characterize friendships …
Paper presents a method for probabilistic load forecasting using adaptive online learning.
problem Inability to assess intrinsic uncertainties and capture dynamic changes in consumption patterns.
method Adaptive online learning of hidden Markov models for recursive parameter updates and sequential prediction.
result Significant improvement in performance compared to existing techniques across various scenarios.
This work improves autonomous racing by creating diverse opponents and adapting risk.
problem Balancing performance and safety in autonomous racing environments.
method Developed a self-play method using replica-exchange Markov chain Monte Carlo for diverse opponents and a distributionally robust bandit optimization for adaptive risk adjustment.
result Demonstrated real-time motion-planning methods achieving speeds comparable to Formula One racecars.
Paper develops algorithms for PWA systems with polynomial regret.
problem Learning in piecewise affine systems due to discontinuities.
method Smoothed online learning framework applied to PWA systems.
result First algorithms with polynomial regret in PWA systems.
Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibrationstat.ML
Proposes a compensation mechanism for improving individual forecast confidence.
problem Difficult to assess the quality of individual probabilistic forecasts and their utilities.
method Compensation mechanism based on fair bets and online learning.
result The proposed mechanism cannot be exploited and ensures forecasted utility matches actual utility.
TensorPlan shows an exponential lower bound for planning in MDPs with linearly realizable value functions.
problem Finding an exponential lower bound for planning in MDPs with linearly realizable value functions.
method TensorPlan and a few action lower bound approach.
result An exponentially large lower bound is shown for planning in MDPs with linearly realizable value functions.
Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
New -Coverage objective simplifies exploration in reinforcement learning.
problem Challenges in exploration for high-dimensional domains.
method Introduces -Coverage objective to enable efficient exploration and planning.
result First computationally efficient algorithms for online reinforcement learning with low coverability.