CoTj improves diffusion model quality and stability via graph planning.
problem Rigidity in diffusion models due to high-dimensional state space.
method Chain-of-Trajectories (CoTj) framework using Diffusion DNA for graph planning.
result CoTj discovers context-aware trajectories improving output quality and stability.
Under mild regularity assumptions, the transport problem is stable in the following sense: if a sequence of optimal transport plans π1,π2,… converges weakly to a transport plan π, then π is also optimal (between its marginals). Alfonsi, Corbetta and Jourdain asked whether the same property is true for th…
New algorithm for planning in observable POMDPs in quasi-polynomial time.
problem Planning in POMDPs is computationally hard.
method Assumption of well-separated distributions on states and observations leads to quasi-succinct descriptions of near-optimal policies.
result Quasipolynomial-time algorithm for planning in observable POMDPs.
The paper analyzes stability and convergence rates of entropic and Sinkhorn potentials.
problem Stability and convergence rates of entropic and Sinkhorn potentials.
method Semiconcavity properties of entropic potentials and Schrödinger bridges.
result Exponential convergence rates for gradient and Hessian of Sinkhorn iterates.
MuZero visualizes its internal representations to stabilize planning.
problem Stability issues in MuZero's planning process.
method Visualized MuZero's latent representations and proposed regularization techniques.
result Action trajectories diverge between observation embeddings and internal state transitions, leading to instability.
Future grid scenario analysis requires a major departure from conventional power system planning, where only a handful of most critical conditions is typically analyzed. To capture the inter-seasonal variations in renewable generation of a future grid scenario necessitates the use of computationally intensive time-seri…
This paper studies when particle filtering is efficient for planning in partially observed systems.
problem The efficiency of particle filtering for planning in partially observed linear dynamical systems.
method Coupling of ideal and approximate sequences to bound particle complexity.
result Polynomially many particles suffice for stable systems to approximate optimal planning.
The paper analyzes reinsurance strategies in peer-to-peer insurance schemes.
problem Strategic interaction between plan managers and reinsurers in P2P insurance.
method Develops two game-theoretic contract designs: Pareto and Bowley designs, deriving optimal contracts and analyzing their welfare effects.
result The Bowley design yields a unique optimal contract, while the Pareto design allows for multiple Pareto-optimal contracts.
This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularize…
New stability bounds for Sinkhorn's algorithm in entropic optimal transport.
problem Stability and convergence of Sinkhorn's algorithm for entropic optimal transport.
method Semiconcavity approach to analyze stability and convergence.
result Exponential convergence of Sinkhorn's algorithm under semiconcavity conditions.
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…
New framework formalizes estimating valid transport maps, revealing their statistical limits.
problem Estimating valid transport maps in generative modeling.
method Formalized a minimax framework for estimating valid transport maps.
result Estimating any valid transport map is as hard as estimating the optimal transport map under standard stability assumptions.
This work enables UAVs to autonomously form desired trajectories without needing a central plan.
problem Autonomous formation of complex trajectories in UAVs.
method Decentralized control system using geometric embeddings.
result Quadcopters self-organize into desired trajectories while maintaining separation.
DTM improves dLLM fine-tuning stability and performance.
problem Intractable sequence-level marginal likelihoods for masked diffusion models.
method Discrete Tilt Matching (DTM) recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting.
result DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.
New RL algorithm ensures stable, replicable policies.
problem Stability and replicability issues in RL algorithms.
method Introduced weak and strong forms of list replicability, developed a novel planning strategy, and tested state reachability.
result Proved efficient tabular RL algorithm with polynomial list complexity.
The paper tackles model misspecification in reinforcement learning through a bootstrapped neural network and error correction.
problem Model misspecification in reinforcement learning environments.
method Proposes a bootstrapped multi-headed neural network to learn model distributions and a global error correction filter.
result Demonstrates increased performance and stability in model accuracy and planning algorithm use.
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we…
The paper analyzes how mutable blockchain protocols affect miner behavior and strategic stability.
problem The mutability of blockchain protocols undermines long-term planning and cooperative equilibria.
method Integrates Austrian capital theory with repeated game theory to examine miner behavior under different institutional conditions.
result Effective time preference increases when protocol rules are mutable, leading to political rent-seeking and undermining strategic coherence.
SRL embeds combinatorial optimization into RL for better decision-making.
problem Challenges of standard RL in complex, structured decision-making problems.
method Structured Reinforcement Learning (SRL) with combinatorial optimization layers in actor neural network.
result SRL outperforms unstructured RL and imitation learning by up to 92% on dynamic problems.
DiffSlack learns neural networks with nonlinear constraints via learnable slack variables.
problem Enforcing nonlinear inequality constraints in neural networks.
method DiffSlack reformulates inequalities as equalities with learnable slack variables, predicting them as part of the network output.
result DiffSlack achieves higher planning success rates and stronger geometric constraint satisfaction compared to existing methods.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
New method designs fairer transport plans with uncertainty.
problem Designing fair and balanced mass transport plans.
method Hierarchical fully probabilistic design (HFPD) for transport plans.
result Optimal hyperprior for transport plans with uncertain marginals.
We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains, such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then trans…
Study integrates reliability constraints into generation planning models.
problem Challenges in integrating reliability constraints with generation planning models.
method Leverages a weighted oblique decision tree (WODT) technique to embed reliability verification constraints.
result Demonstrates effectiveness in achieving reliable and optimal planning solutions.
New approach improves black-box planning efficiency by discovering focused macros.
problem Difficulty of deterministic planning increases exponentially with depth.
method Discovering macro-actions with focused effects to improve goal-count heuristics.
result Focused macros dramatically improve black-box planning efficiency.
Study motion planning for points avoiding obstacles in a plane.
problem Avoiding collisions for multiple points in a plane with unknown obstacles.
method Algebraic and topological tools for motion planning.
result New topological complexity for planar motion planning.
Unified framework explains retirement and annuitization decisions under age-dependent mortality.
problem Complexity of annuitization decisions due to longevity risk and labor force participation.
method Stochastic control and optimal stopping framework with habit formation and endogenous labor supply.
result Rich sequence of retirement dynamics, including defensive and aggressive labor supply phases.
Selective planning with imperfect models reduces harmful effects of model inadequacy.
problem Harmful effects of using an imperfect model in reinforcement learning.
method Selective planning with heteroscedastic regression to estimate predictive uncertainty from model inadequacy.
result Effective selective planning requires considering both parameter uncertainty and model inadequacy.
CoMPNetX uses neural networks to efficiently solve constrained motion planning problems.
problem Finding collision-free paths on constraint manifolds efficiently.
method Neural generator and discriminator with neural gradients-based projection operator.
result CoMPNetX finds path solutions with high success rates and lower computation times.
This article asks how planning scholarship may effectively gain impact in planning practice through media exposure. In liberal democracies the public sphere is dominated by mass media. Therefore, working with such media is a prerequisite for effective public impact of planning research. Using the example of megaproject…
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 method combines heuristics and search techniques to speed up cooperative planning for autonomous vehicles.
problem Efficient cooperative planning for autonomous vehicles in complex traffic scenarios.
method Combining learned heuristics with Monte Carlo Tree Search (MCTS) to guide search towards promising actions.
result Better solutions at lower computational costs achieved through accelerated planning.
This paper presents a unifying framework for reinforcement learning and planning.
problem Sequential decision making in AI, formalized as MDP optimization.
method A unifying algorithmic framework (FRAP) for reinforcement learning and planning.
result Identifies common dimensions in MDP planning and learning algorithms.
A planning approach learns skills from interactions, balancing exploration and exploitation.
problem Learning robust high-level skills in noisy environments with unknown pre-conditions.
method Formulates skills as high-level policies, learns plans via bandit problems, balances exploration and exploitation.
result A planner capable of learning robust high-level skills in high-dimensional state spaces.
Survey of integrating planning and learning in model-based reinforcement learning.
problem Sequential decision making in AI, formalized as MDP optimization.
method Systematic coverage of dynamics model learning and planning-learning integration.
result Broad conceptual overview of model-based reinforcement learning.
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue…
New approach for obstacle avoidance in robotics using learned representations.
problem Challenges in sensor-based motion planning for new and dynamic environments.
method Proposes a new obstacle representation using PointNet architecture trained jointly with policies for obstacle avoidance.
result Significant improvements in accuracy and efficiency compared to state of the art.
Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may …
A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a for…
This work clarifies the role of inference types in planning.
problem Lack of consistency in using inference types for planning.
method Variational framework and loopy belief propagation.
result All inference types correspond to different weights in variational problems.
In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …
This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
problem Current learning approaches fail on long-horizon tasks due to lack of goal information and coarse-to-fine planning.
method Formulate goal-conditioned predictors (GCPs) and hierarchical models to predict trajectories between observations.
result GCPs enable effective long-term planning with much longer horizons than before.
Knowledge-based planning (KBP) is an automated approach to radiation therapy treatment planning that involves predicting desirable treatment plans before they are then corrected to deliverable ones. We propose a generative adversarial network (GAN) approach for predicting desirable 3D dose distributions that eschews th…
We designed a grid world task to study human planning and re-planning behavior in an unknown stochastic environment. In our grid world, participants were asked to travel from a random starting point to a random goal position while maximizing their reward. Because they were not familiar with the environment, they needed…
This work defines a complexity measure for BAMDP planning and introduces state abstraction for more efficient approximate planning.
problem The computational intractability of exact BAMDP planning solutions.
method Define a complexity measure for BAMDP planning, introduce state abstraction, and develop an approximate planning algorithm.
result Introduces a computationally tractable approximate planning algorithm using state abstraction.
With the growth of renewable generation (RG) and the development of associated ride through curves serving as operating limits, during disturbances, on violation of these limits, the power system is at risk of losing large amounts of generation. In order to identify preventive control measures that avoid such scenarios…
Information planning enables faster learning with fewer training examples. It is particularly applicable when training examples are costly to obtain. This work examines the advantages of information planning for text data by focusing on three supervised models: Naive Bayes, supervised LDA and deep neural networks. We s…
PALM learns abstract models for efficient planning and task transfer.
problem Efficiently learning and transferring hierarchical models for planning.
method PALM uses a new formal structure (L-AMDP) to learn independent, modular models at multiple levels of abstraction.
result PALM integrates planning and execution, facilitating rapid learning of abstract models.