We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learni…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “long-horizon tasks”
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templatescs.LG
Framework uses expert intervention to solve long-horizon reinforcement learning tasks.
problem Long horizon robot learning tasks with sparse rewards.
method Option templates and expert intervention to enable high-level task understanding.
result Framework outperforms state-of-the-art approaches by two orders of magnitude.
Max entropy exploration guides reinforcement learning agents to pursue achievable goals.
problem Achieving distant test-time goals in long-horizon tasks.
method Optimize entropy of historical achieved goals by focusing on sparsely explored areas.
result Order of magnitude better sample efficiency on long-horizon multi-goal tasks.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
Accelerates TD learning for long-horizon reinforcement learning problems.
problem Slow convergence of conventional TD learning in long-horizon tasks.
method Introduces PID Accelerated Temporal Difference (PID TD) learning algorithms.
result Accelerates convergence of TD learning compared to conventional methods.
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.
Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generationcs.LG
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor s…
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to properly memorize and utilize the long-term history is crucial. In this work, we pro…
FDS tackles long horizon hyperparameter optimization issues.
problem Memory scaling and gradient degradation in long horizon tasks.
method Forward-mode differentiation with sharing (FDS).
result Significantly outperforms greedy gradient-based alternatives.
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…
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.
TRM improves long-horizon LLM RL by masking divergent sequences.
problem Long-horizon reinforcement learning with LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
TRM improves long-horizon reinforcement learning for LLMs by masking divergent sequences.
problem Long-horizon reinforcement learning for LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.
HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulatorscs.LG
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
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.
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…
Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated action…
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
Q-chunking improves RL for long tasks by chunking actions.
problem Improving sample efficiency and exploration in offline-to-online RL.
method Action chunking in TD-based RL methods.
result Q-chunking outperforms prior methods on long-horizon tasks.
Predicts long-term return distributions with time-varying volatility.
problem Risk management in long-horizon returns.
method Predicts future return distributions without specifying volatility dynamics or shock distribution.
result Derives risk measures like VaR and CTE from the predicted return distribution.
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…
New method produces coherent forecasts for long-range data.
problem Inaccurate and non-coherent forecasts on long-horizon data.
method Probabilistic forecasting with KL-divergence for coherent aggregates.
result Improves forecast performance across base levels and aggregates.
This review tackles long horizon forecasting in time series analysis using deep learning.
problem Long horizon forecasting in time series analysis.
method Incorporates deep learning techniques such as trend, seasonality, Fourier and wavelet transforms, and various model architectures.
result LHF is an error propagation problem, with models like xLSTM and Triformer showing better performance.
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.
Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?cs.LG
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.
LLapDiff models irregular multivariate time series without step-by-step integration.
problem Trade-off between discrete and continuous methods for long-horizon forecasting.
method Generative framework that models target as a low-dimensional latent trajectory, guided by modal parameterization and Laplace domain poles.
result Improves long-horizon forecasting over baselines and supports missing-value imputation.
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.
Action-bisimulation learns long-horizon controllability for reinforcement learning.
problem Learning relevant state features in high-dimensional observations for robust reinforcement learning.
method Action-bisimulation encoding, inspired by bisimulation invariance, extends single-step controllability to multi-step.
result Action-bisimulation pretraining improves sample efficiency in various environments.
Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…
The paper clarifies long-horizon investment and DCA, showing no risk reduction but different exposure profiles.
problem Misleading claims about reducing risk with longer investment horizons and DCA.
method Unified probabilistic framework, defining risk and uncertainty, and introducing effective investment exposure.
result Different investment timing strategies can lead to distinct exposure profiles over time, affecting risk and uncertainty.
Temporal Coarse-Graining of Latent Default-Probability Paths Generates Effective Default Correlationq-fin.ST
Temporal aggregation reveals latent default correlation from monthly data.
problem Understanding effective default correlation from monthly default data.
method Temporal coarse-graining of latent default-probability paths.
result Temporal coarse-graining improves identifiability and reduces over-allocation of long-horizon fluctuations.
Temporal Coarse-Graining of Latent Default-Probability Paths Generates Effective Default Correlationq-fin.ST
Temporal coarse-graining of latent default paths explains effective correlation in corporate defaults.
problem Understanding effective default correlation in corporate defaults.
method Temporal coarse-graining of latent default-probability paths, applied to corporate default-count data.
result Temporal coarse-graining provides a scale-consistent baseline that improves identifiability and reduces over-allocation of long-horizon fluctuations.
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.
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.
For an investor with constant absolute risk aversion and a long horizon, who trades in a market with constant investment opportunities and small proportional transaction costs, we obtain explicitly the optimal investment policy, its implied welfare, liquidity premium, and trading volume. We identify these quantities as…
Compositional diffusion models simulate coupled PDEs efficiently.
problem Efficiently simulating long-horizon coupled PDE systems.
method Diffusion models trained on decoupled data are composed at inference time.
result Compositional diffusion models recover coupled trajectories with low error.
Behavior cloning training instabilities amplified by SGD noise over long horizons.
problem Training instabilities in behavior cloning with deep neural networks.
method Empirical dissection of minibatch SGD updates and their effects on long-horizon rewards.
result Exponential moving average (EMA) of iterates effectively mitigates gradient variance amplification (GVA).
A new model decomposes equity returns and volatilities into memory components.
problem Understanding long-term equity dynamics and volatility patterns.
method Proposes a multivariate generalization of the variance ratio to decompose long-horizon equity dynamics.
result Identifies a five-factor model capturing persistent, antipersistent, and multi-scale memory in returns and volatility.
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.
MO2 learns useful behaviours from past experience for new tasks.
problem Discovering useful behaviours from past experience and transferring them to new tasks.
method Model-Based Offline Options (MO2) framework supporting sample-efficient bottleneck option discovery over continuous state-action spaces.
result MO2 outperforms recent option learning methods on complex long-horizon continuous control tasks.
A framework for learning disentangled representations of symmetric environments.
problem Discovering and modelling the underlying structure of environments.
method Group representation theory for disentangled representations of dynamical environments.
result Our method enables accurate long-horizon predictions and correlates with disentanglement quality.
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can le…
We consider a market consisting of one safe and one risky asset, which offer constant investment opportunities. Taking into account both proportional transaction costs and linear price impact, we derive optimal rebalancing policies for representative investors with constant relative risk aversion and a long horizon.
DMIDAS improves long-term forecasting accuracy in healthcare and electricity data.
problem Challenging long-term forecasting accuracy and computational complexity.
method Smoothness regularization and mixed data sampling techniques integrated into NBEATS architecture.
result Improves prediction accuracy by 5% on long forecasting horizons (1000 timestamps) compared to state-of-the-art models.
New algorithms for efficient learning with long-term rewards in contextual bandits.
problem Efficient learning with long-term rewards in contextual bandits.
method Proposes new algorithms leveraging sparsity to discover dependence patterns and arm parameters.
result Regret upper bounds for data-poor and data-rich regimes, showing improved sample complexity.
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exasperated in problems with long horizons or high-dimensional action spaces. To mitigate this issue, we derive a bias-free action-dependent ba…
Financial event studies often misestimate causal effects due to misspecified factor models.
problem Misspecification of factor models in financial event studies leads to inconsistent estimates of causal effects.
method Proposed synthetic control methods to construct replicating portfolios from control securities.
result Synthetic control methods provide more accurate estimates of causal effects in event studies.
CausalWorld benchmarks robotic manipulation tasks with causal structure for transfer learning.
problem Challenges in transferring learned skills to new robotic manipulation environments.
method Proposes a simulation-based benchmark with a combinatorial family of tasks.
result Demonstrates the feasibility of tasks in the benchmark and provides baseline results.