PlaNet learns latent dynamics from images for better planning in unknown environments.
problem Leveraging planning in unknown environments with accurate dynamics models.
method Deep Planning Network (PlaNet) learns dynamics from images using latent space and multi-step variational inference.
result PlaNet achieves high performance in continuous control tasks with contact dynamics and sparse rewards.
DPN combines model-based and model-free reinforcement learning for efficient planning.
problem Efficiently plan actions in reinforcement learning environments.
method Combines model-based and model-free reinforcement learning, dynamically constructing plans using a learned state-transition model.
result Reduces the number of state transitions during planning by up to 96%, improving data efficiency and performance.
New method uses autoregressive models for dynamic planning.
problem Planning in dynamic environments with moving obstacles and goals.
method Conditional autoregressive generative models in a discrete latent space.
result Method nearly matches true environment performance for planning.
Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
Regularizes model-based planning using energy-based models for efficient learning.
problem Challenges in using learned dynamics models for accurate planning.
method Regularization using energy estimates of state transitions.
result Proposes effective regularization method for planning with pre-trained dynamics models.
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.
AOP combines model-based planning with model-free learning to handle lifelong learning challenges.
problem Learning control in an online reset-free lifelong learning scenario where mistakes can compound and dynamics change.
method Adaptive Online Planning (AOP) that combines model-based planning with model-free learning, approximating uncertainty to call upon planning only when necessary.
result Achieves strong performance in lifelong learning challenges, gracefully adapting behaviors in the face of unpredictable changes.
New algorithm models satiation in recommender systems.
problem Satiation effects in user preferences not modeled by existing algorithms.
method Rebounding bandits, modeling satiation as time-invariant linear dynamical systems.
result Greedy policy optimal for identical deterministic dynamics; EEP algorithm for stochastic dynamics.
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.
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.
New method for optimistic planning in MDPs using regularization.
problem Optimistic planning in infinite-horizon discounted MDPs.
method Regularized dynamic programming for approximate value iteration.
result Achieves near-optimal statistical guarantees in learning policies.
Greedy policies in model-based RL achieve tight regret bounds without full planning.
problem Achieving efficient RL algorithms in MDP settings.
method Using greedy policies for 1-step planning in model-based RL.
result Greedy policies achieve i l d e O ( H S A T ) ilde{\mathcal{O}}(\sqrt{HSAT}) i l d e O ( H S A T ) regret bounds. Paper proposes Imitative Models combining IL and planning for flexible goal achievement.
problem Difficult to direct IL to arbitrary goals and specify reward functions for goal-directed planning.
method Imitative Models are probabilistic predictive models that plan interpretable expert-like trajectories.
result Imitative Models outperform IL and planning approaches in a dynamic autonomous driving task.
This paper optimizes DC pension plan investments using O-U process and loan.
problem Optimizing investment strategy for DC pension plans under specific market conditions.
method Dynamic programming and Hamilton-Jacobi-Bellman equation to derive optimal investment strategy.
result Explicit expression for optimal investment strategy derived.
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.
problem Learning accurate models for complex dynamical systems is difficult and often doesn't generalize well.
method Dynamics-Aware Discovery of Skills (DADS) combines model-based and model-free learning.
result DADS discovers infinitely many behaviors in high-dimensional state-spaces.
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.
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 …
The paper introduces a method to create more reliable models for robot dynamics.
problem Creating accurate models for robot dynamics to improve control and planning algorithms.
method A primal-dual method to enforce constraints on error in specific parts of the state-space.
result The learned models have more predictable error characteristics, enhancing their usability for planning and control algorithms.
Improved online planning with lookahead policies for large state spaces.
problem Online planning with large state spaces and limited state updates.
method Developed h h h -RTDP algorithm with h h h -step lookahead policy. result Improved sample complexity with increased lookahead horizon.
Unified approach to path planning using probabilistic inference on factor graphs.
problem Path planning problems using probabilistic inference.
method Unified framework using probabilistic factor graphs and message composition rules.
result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.
MuZero learns models to master complex games without domain knowledge.
problem Mastering complex, real-world domains with unknown dynamics.
method Combining tree-based search with learned models.
result Achieves superhuman performance in diverse domains.
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.
Proposes a method for model-based RL in complex environments without perfect simulators.
problem Lack of cheap and perfect simulators in real-world tasks.
method Induces a world program by learning dynamics and actions in graph-based environments.
result World program enables complex planning tasks in 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.
problem Systematic biases in LLMs lead to inefficient and unsafe search in deep planning tasks.
method Formulates node expansion as BAI under bounded bias, derives sample complexity bounds, and proposes PAC-MCTS for dynamic confidence bounds.
result PAC-MCTS improves robustness and efficiency by up to 78% fewer API evaluations and 3x higher sample efficiency.
EBMs improve sample efficiency and generalization in RL.
problem Improving sample efficiency and generalization in reinforcement learning.
method Developed an online algorithm to train EBMs for model-based planning, leveraging their ability to infer intermediate states.
result EBMs lead to significantly better online learning and state space planning compared to feed-forward networks.
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.
problem Improving credit assignment in reinforcement learning.
method Investigates the use of forward and backward models for planning in reinforcement learning.
result Establishes the relative merits and limitations of forward and backward planning mechanisms.
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.
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.
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…
iDriveSense offers safer trip recommendations by considering road anomalies.
problem Drivers seek safer routes despite shortest/fastest path recommendations.
method Crowdsensing, vehicle sensors, fuzzy systems for road quality assessment.
result Proposes a system for dynamic route planning considering road anomalies.
Improves model-based control and exploration by estimating model uncertainty.
problem Inaccuracies in model predictions lead to frequent re-planning, inefficiency, and unreliability.
method Estimates model uncertainty using reconstruction error and uses it for better control and active exploration.
result Improves control performance and exploration efficiency by choosing confident model predictions and planning for high uncertainty.
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.
Improved motion planning for dynamic environments using RL.
problem Efficient motion planning in changing environments.
method Deep reinforcement learning (DDPG) tailored for motion planning.
result DDPG-MP significantly improves motion planning accuracy.
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.
problem Learning in environments where contexts change over time.
method Dynamic Contextual Markov Decision Processes (DCMDPs) with logistic aggregation.
result Upper-confidence-bound style algorithm with regret bounds.
The paper tackles model-based RL's inaccuracy issue by dynamically adjusting planning horizons.
problem Model-based RL's failure due to model inaccuracy over long planning horizons.
method State-dependent planning horizon, learning cumulative model errors with Temporal Difference methods.
result The proposed method successfully adapts planning horizons to state-dependent model accuracy, improving policy learning efficiency.
Efficiently computes optimal policies for Entropic Risk Measures.
problem Optimizing risk-sensitive metrics in MDPs is computationally expensive.
method Uses Entropic Risk Measures and novel structural analysis for efficient computation.
result Achieves strong performance in various decision-making scenarios.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
Develops a method to plan exploration that learns strong policies with fewer samples.
problem Lack of efficient exploration in reinforcement learning for real-world tasks.
method Plans an action sequence that maximizes information gain about the optimal trajectory.
result 2x fewer samples than exploration baselines and 200x fewer than model-free methods.
This work proposes a RL approach to learn versatile robotic manipulation tasks.
problem Challenging manipulation tasks in robotics and vision.
method Reinforcement learning (RL) to combine primitive skills, no intermediate rewards, few demonstrations, and efficient skill learning.
result Versatile robotic manipulation in challenging settings with temporary occlusions and dynamic scene changes.
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.
problem Planning in high-dimensional state spaces with limited reward information.
method Directly learns a latent dynamics model from rewards, planning in latent state-space.
result Successfully learns accurate latent reward prediction model, achieving strong performance and high sample efficiency.
Improved API to achieve optimal error bound and query complexity in local planning.
problem Efficient local planning in discounted MDPs with linear approximation.
method Confident Approximate Policy Iteration (CAPI) for stationary policies, applying to local access simulators.
result Achieves optimal accuracy and query complexity bounds, improving over API.
Paper proposes exploiting Q function structures for better planning and RL.
problem Value-based methods in planning and RL.
method Exploiting low-rank structure of Q function using Matrix Estimation techniques.
result Improved planning and RL performance on 'low-rank' tasks.