arXiv research

DPN combines model-based and model-free reinforcement learning for efficient planning.

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…

Proposes DLGPD model to learn dynamics from images for planning.

Regularizes model-based planning using energy-based models for efficient learning.

This paper studies when particle filtering is efficient for planning in partially observed systems.

AOP combines model-based planning with model-free learning to handle lifelong learning challenges.

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obst…

New algorithm models satiation in recommender systems.

This paper presents preliminary work on learning the search heuristic for the optimal motion planning for automated driving in urban traffic. Previous work considered search-based optimal motion planning framework (SBOMP) that utilized numerical or model-based heuristics that did not consider dynamic obstacles. Optimal…

Survey of integrating planning and learning in model-based reinforcement learning.

New method for optimistic planning in MDPs using regularization.

Greedy policies in model-based RL achieve tight regret bounds without full planning.

This paper optimizes DC pension plan investments using O-U process and loan.

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples f…

DADS discovers skills with predictable outcomes from unlabeled data.

New algorithm for planning in observable POMDPs in quasi-polynomial time.

New approach for obstacle avoidance in robotics using learned representations.

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 …

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…

The paper introduces a method to create more reliable models for robot dynamics.

Improved online planning with lookahead policies for large state spaces.

Unified approach to path planning using probabilistic inference on factor graphs.

MuZero learns models to master complex games without domain knowledge.

Improves RL planning by proposing sub-goals hierarchically.

Proposes a method for model-based RL in complex environments without perfect simulators.

We study the dynamic assortment planning problem, where for each arriving customer, the seller offers an assortment of substitutable products and customer makes the purchase among offered products according to an uncapacitated multinomial logit (MNL) model. Since all the utility parameters of MNL are unknown, the selle…

PAC-MCTS addresses biased search in LLM-guided planning by dynamically pruning.

EBMs improve sample efficiency and generalization in RL.

Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and prove for certain environments the algorithm is probably approximately correct wit…

The paper explores how planning with models improves credit assignment in reinforcement learning.

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 …

CoTj improves diffusion model quality and stability via graph planning.

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…

Improves model-based control and exploration by estimating model uncertainty.

MuZero visualizes its internal representations to stabilize planning.

Improved motion planning for dynamic environments using RL.

Owing to the expeditious growth in the information and communication technologies, smart cities have raised the expectations in terms of efficient functioning and management. One key aspect of residents' daily comfort is assured through affording reliable traffic management and route planning. Comprehensively, the majo…

For any business, planning is a continuous process, and typically business-owners focus on making both long-term planning aligned with a particular strategy as well as short-term planning that accommodates the dynamic market situations. An ability to perform an accurate financial forecast is crucial for effective plann…

New framework handles dynamic contexts in reinforcement learning.

The paper tackles model-based RL's inaccuracy issue by dynamically adjusting planning horizons.

Efficiently computes optimal policies for Entropic Risk Measures.

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

Develops a method to plan exploration that learns strong policies with fewer samples.

This work proposes a RL approach to learn versatile robotic manipulation tasks.

Learning and inference movement is a very challenging problem due to its high dimensionality and dependency to varied environments or tasks. In this paper, we propose an effective probabilistic method for learning and inference of basic movements. The motion planning problem is formulated as learning on a directed grap…

Proposes learning latent reward model for planning from rewards.

Improved API to achieve optimal error bound and query complexity in local planning.

Paper proposes exploiting Q function structures for better planning and RL.