Hierarchical Foresight improves robot vision tasks by planning long-term goals.
problem Compounding uncertainty and scalability issues in long horizon video prediction.
method Subgoal generation and planning using hierarchical visual foresight (HVF).
result Achieves nearly 200% performance improvement in vision-based manipulation tasks.
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.
Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.
problem Optimizing behavior for long-term goals in reinforcement learning with unstable long planning horizons.
method Reward tweaking learns a surrogate reward function that induces optimal behavior for the original task.
result Reward tweaking guides agents towards better long-term returns while planning for short horizons.
SGM combines deep learning and planning for robust long-horizon tasks.
problem Combining deep learning and planning for robust long-horizon tasks.
method Sparse Graphical Memory (SGM) that stores states and feasible transitions in a sparse memory, aggregating states according to a two-way consistency objective.
result SGM significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
Long horizon reinforcement learning is as hard as short horizon learning.
problem Understanding the difficulty of long horizon reinforcement learning problems.
method Introduced new concepts: ε-net for optimal policies and Online Trajectory Synthesis algorithm.
result Proved that sample complexity scales logarithmically with the planning horizon, refuting the conjecture.
The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires flexible generative planning that can combine primitive abilities in novel combination…
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.
Agents compose pre-trained policies for complex tasks, improving zero-shot performance.
problem Challenges in long-horizon predictions and estimating visitation distributions induced by policy sequences.
method Learn predictive jumpy world models of multi-step dynamics, enhancing predictions with a consistency objective.
result Compositional planning with jumpy world models yields, on average, a 200% relative improvement over primitive actions on long-horizon tasks.
UCRL-WVTR tackles long-term reinforcement learning with general approximations, achieving horizon-free and instance-dependent regret bounds.
problem Long-term reinforcement learning with general function approximations.
method UCRL-WVTR proposes a novel algorithm, UCRL-WVTR, with weighted value-targeted regression and a high-order moment estimator.
result Achieves horizon-free and instance-dependent regret bounds matching minimax lower bounds up to logarithmic factors.
TD-Flow improves long-term predictions in agent learning.
problem Cumulative errors in step-by-step inference of future states.
method Leverages flow-matching techniques and a novel Bellman equation to learn accurate geometric horizon models.
result Significantly reduces errors at long horizons compared to prior methods.
HiDe learns hierarchical control for complex tasks by separating planning and control.
problem Solving long horizon control tasks with generalization to unseen scenarios.
method Functional decomposition of state-action spaces, RL-based planner, modular transfer of policy layers.
result Generalizes across unseen test environments and scales to longer horizons.
When the planning horizon is long, and the safe asset grows indefinitely, isoelastic portfolios are nearly optimal for investors who are close to isoelastic for high wealth, and not too risk averse for low wealth. We prove this result in a general arbitrage-free, frictionless, semimartingale model. As a consequence, op…
New algorithm for RL with horizon-free reward-free exploration for linear MDPs.
problem Reward-free reinforcement learning with long planning horizons.
method Uncertainty-weighted value-targeted regression with exploration-driven pseudo-reward and moment estimator.
result Horizon-free sample complexity of O(d2ε−2) for finding an ε-optimal policy. New algorithm reduces reinforcement learning complexity, approaching contextual bandits.
problem Episodic reinforcement learning's difficulty compared to contextual bandits.
method Proposes MVP algorithm with a new Bernstein-type bonus for episodic reinforcement learning.
result Achieves near-optimal regret bound of $O\left(\left(\sqrt{SAK} + S^2A
ight) \poly\log \left(SAHK
ight)
ight)$, improving state-of-the-art results.
The hierarchical structure of production planning has the advantage of assigning different decision variables to their respective time horizons and therefore ensures their manageability. However, the restrictive structure of this top-down approach implying that upper level decisions are the constraints for lower level …
In this paper, we propose to combine imitation and reinforcement learning via the idea of reward shaping using an oracle. We study the effectiveness of the near-optimal cost-to-go oracle on the planning horizon and demonstrate that the cost-to-go oracle shortens the learner's planning horizon as function of its accurac…
We consider the portfolio choice problem for a long-run investor in a general continuous semimartingale model. We suggest to use path-wise growth optimality as the decision criterion and encode preferences through restrictions on the class of admissible wealth processes. Specifically, the investor is only interested in…
Plan2Vec learns image representations without labels, improving control tasks.
problem Learning image representations without labeled data.
method Constructs a weighted graph using near-neighbor distances and extrapolates to global embedding.
result Plan2Vec achieves accurate long-term value estimates in control tasks with reduced computational and memory costs.
Paper proposes a reinforcement learning method for efficient information acquisition.
problem Solving the Active Information Acquisition problem for robotic systems.
method Reinforcement Learning approach to choose actions for acquiring information.
result Efficient policies for online execution and real-time control of robotic systems.
Study forecasts sub-city real estate prices weekly using radar and news sentiment.
problem Limited availability of reliable real estate price indicators at neighborhood and long horizons.
method Combining satellite radar signals and news sentiment to forecast sub-city real estate prices.
result The multimodal model reduces mean absolute error by 35% at long horizons (26-34 weeks).
New ML model predicts long-term power generation at large areas.
problem Accurate forecasting of long-term power generation from renewable sources.
method Machine learning model applied to aggregated power generation data.
result The model predicts power generation with high accuracy over 15 days.
Investigates multi-period portfolio optimization for DC plans using buffered Probability of Exceedance.
problem Optimizing long-term Defined Contribution plans with realistic constraints and dynamic dynamics.
method Formulates and solves bilevel optimization problems for pre-commitment and time-consistent Mean-bPoE and Mean-CVaR portfolio optimization.
result Time-consistent Mean-bPoE strategies maintain investor preferences for minimum terminal wealth, unlike Mean-CVaR.
Behavioral theories posit that investor sentiment exhibits predictive power for stock returns, whereas there is little study have investigated the relationship between the time horizon of the predictive effect of investor sentiment and the firm characteristics. To this end, by using a Granger causality analysis in the …
Olympic Games consistently exceed budgets, leading to unpredictable costs.
problem High costs and unpredictability of the Olympic Games.
method Statistical analysis of historical data to explain cost risks.
result Olympic costs follow a power-law distribution with infinite mean and variance.
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.
Optimal timing for borrowing from a 457(b) plan to maximize returns.
problem Deciding the best time to borrow from a tax-advantaged retirement account.
method Formulated and solved the optimal stopping problem for a loan from a 457(b) plan.
result Derived cutoff rules for optimal loan control, showing how to wait until a certain amount of money is accumulated.
RL policy tracks dynamic targets in partially known environments robustly.
problem Active target tracking in partially known environments.
method Deep reinforcement learning (RL) approach for in-sight tracking, navigation, and exploration.
result Unified RL policy shows robust behavior for agile and anomalous targets.
In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to collect the most points while staying alive in the long run. Yet, it may be difficult (or even intractable) mathematically to learn with th…
An accurate load forecasting has always been one of the main indispensable parts in the operation and planning of power systems. Among different time horizons of forecasting, while short-term load forecasting (STLF) and long-term load forecasting (LTLF) have respectively got benefits of accurate predictors and probabil…
Efficient RL for linear MDPs with unknown transitions.
problem Long planning horizons and unknown state transitions in linear mixture MDPs.
method Horizon-free algorithm using weighted least squares with variance and uncertainty awareness.
result Achieves optimal regret up to logarithmic factors.
New research shows exponential lower bounds for planning in MDPs with linearly-realizable optimal action-value functions.
problem Determining the minimum number of queries needed for sound planners in MDPs with linear function approximation.
method Analyzing fixed-horizon and discounted MDPs with a generative model, showing lower bounds on the number of queries required.
result Sound planners need at least exponential number of queries in both fixed-horizon and discounted settings.
The study reveals distinct patterns in retail investors' holding periods affecting stock returns.
problem Understanding the impact of retail investors' investment horizons on stock returns.
method Using self-reported holding periods from StockTwits, the study categorizes retail investors into long-horizon and short-horizon groups and analyzes their return patterns.
result Long-horizon retail investors exhibit underreaction to earnings announcements, while short-horizon investors show overreaction.
The paper predicts travel times using tree-based ensembles.
problem Predicting travel times between urban points over short and long horizons.
method Tree-based ensemble methods trained on taxi trip records with additional features from weather and routing data.
result Adding routing data improves model performance and short-term predictions require less data.
State-of-the-art forecasting methods using Recurrent Neural Net- works (RNN) based on Long-Short Term Memory (LSTM) cells have shown exceptional performance targeting short-horizon forecasts, e.g given a set of predictor features, forecast a target value for the next few time steps in the future. However, in many appli…
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Method solves long-horizon robotic tasks via imitation and reinforcement learning.
problem Long-horizon robotic tasks with complex sequences of actions.
method Two-phase approach: imitation learning followed by reinforcement learning.
result Method can scale to challenging long-horizon tasks.
Improved online planning with lookahead policies for large state spaces.
problem Online planning with large state spaces and limited state updates.
method Developed h-RTDP algorithm with h-step lookahead policy. result Improved sample complexity with increased lookahead horizon.
Deep RL drone trained to compete against classical path planning in drone racing.
problem Optimizing long-term drone racing strategies using reinforcement learning.
method Used PPO algorithm on a simulated quadrotor in a racing environment created with AirSim.
result Deep RL agent outperformed classical path planning in drone racing competitions.
Director learns hierarchical behaviors from pixels, outperforming exploration methods.
problem Challenges in learning long-term hierarchical behaviors from pixels.
method Directly learns hierarchical behaviors from pixels using a latent space world model.
result Director outperforms exploration methods on various tasks.
C-Learning estimates reachability over time to solve multi-goal tasks.
problem Multi-goal reaching challenges in reinforcement learning.
method Cumulative accessibility functions and recurrence relations.
result Optimal cumulative accessibility functions are monotonic in horizon.
Solves risk-aware optimal switching problems in discrete time.
problem Non-Markovian optimal switching problems with risk awareness and general filtration.
method Solves reflected backward stochastic difference equations.
result Existence and uniqueness of solutions for the problems.
Study long-term asset liquidation behavior with external flows.
problem Investigate optimal liquidation in presence of external flows.
method Convergence analysis of BSDEs for value function and strategy.
result Long-term liquidation may not occur due to external flows.
Reservoir computing predicts chaotic systems for long horizons with sparse updates.
problem Predicting chaotic systems with long horizons using limited data.
method Sparse, time-dependent data inputs into reservoir computing.
result Achieves arbitrarily long prediction horizons for chaotic systems.
In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which…
Paper analyzes neural network complexity for planning problems.
problem Understanding neural network complexity for planning policies.
method Circuit complexity analysis for relational neural networks.
result Three classes of planning problems identified based on network complexity.
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past acti…
Cohesion uses deep Koopman operators to generate long-range forecasts of chaotic dynamics.
problem Challenges in data-driven emulation of chaotic dynamics, especially long-range skill decay.
method Generative modeling with coherent priors estimated using reduced-order models.
result Superior long-range forecasting skill on chaotic systems, including climate dynamics.
State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered experience. In this paper, we focus on model-based RL in the finite-state finite-horizon…