Research
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.

168,657 papers · 148 categories

Trend · papers per month

285683111 · Jun 202019922001200920172026
48 results for expert trajectories

Bayesian method estimates dynamics from near-optimal trajectories.

problem Estimating dynamics from near-optimal expert trajectories in reinforcement learning.
method Constraint-based Bayesian approach integrating expert near-optimality.
result Significant improvements in decision-making and transfer success.

Paper proposes a reinforcement learning method for trading using expert trajectories.

problem Inability of existing methods to handle long-term goals and delayed rewards in futures trading.
method Modeling futures trading as MDP, using reinforcement learning with expert trajectories and multiple short-term alpha factors.
result The proposed method outperforms traditional and deep learning methods in trading performance.

Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…

2019-11-03abs ↗pdf ↗

The paper provides theoretical guarantees for behavior cloning using generative models.

problem Behavior cloning of complex expert demonstrations using generative models.
method The paper proposes a theoretical framework invoking low-level controllers to stabilize imitation around expert demonstrations. It shows that with suitable low-level stability guarantees and powerful generative models, pure supervised behavior cloning can match expert trajectories.
result The paper proves that with a suitable low-level stability guarantee and a powerful enough generative model, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost.

New method recovers diverse policies from expert data using state-action pair weighting.

problem Recovering diverse policies from expert trajectories.
method Pointwise mutual information weighted behavioral cloning.
result Effective in focusing on state-action pairs most representative of the style.

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods for reward estimation by using expert state trajectories and action pairs. However…

2018-06-02abs ↗pdf ↗

GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.

problem Efficiently solving Stochastic Optimal Transport with hard terminal distributions and soft costs.
method Guided Harmonic Path-Integral Diffusion (GH-PID) framework with low-dimensional guidance.
result GH-PID generates geometry-aware, cost-reducing trajectories that match terminal distributions.

The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action planning, current methods mostly rely on two requirements: exactly-relevant expert demonstrations or the explicitly-coded cost function on targe…

2018-05-12abs ↗pdf ↗

The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations. In this article, we study this fundamental problem in the framework of energy-based model, where the observed expert trajectori…

2019-04-10abs ↗pdf ↗

We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL). Motivated by a limitation of the classical maximum entropy model in capturing the structure of the network of states, we propose an IRL model based on a generalized version of the causal entropy maximization pr…

2019-11-16abs ↗pdf ↗

Paper uses deep imitation learning to predict aircraft trajectories accurately.

problem Inefficient and costly Air Traffic Management system limits predictability.
method Generative Adversarial Imitation Learning framework with trajectory clustering and classification.
result Accurate predictions for entire trajectory stages, pre- and tactical.

Online Apprenticeship Learning aims to match expert performance without access to cost functions.

problem Learning an agent's policy to match expert performance in an MDP without cost function access.
method Combines mirror descent based no-regret algorithms for policy optimization and cost learning, with optimistic exploration.
result Derives an algorithm with O(K)O(\sqrt{K}) regret, practical for high-dimensional control problems.

A method merges two pretrained diffusion experts to improve image quality and likelihood.

problem Trade-off between image quality and data likelihood in diffusion models.
method Combining two pretrained diffusion experts by switching between them along the denoising trajectory.
result The merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality.

We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing trajectory data or information occurs in many situations, e.g., GPS signals from vehicl…

2019-11-16abs ↗pdf ↗

GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.

problem Cross-domain imitation learning challenges due to different system dimensions and stationary distributions.
method Gromov-Wasserstein Imitation Learning (GWIL) using Gromov-Wasserstein distance.
result GWIL effectively aligns expert and imitation agent states in various continuous control domains.

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle, difficult to use and tune, and sensitive to seemingly innocuous implementation decis…

2019-12-31abs ↗pdf ↗

Continuous control imitation learning fails if expert actions are smooth.

problem Continuous control imitation learning fails if expert actions are smooth.
method Study of imitation learning in discrete-time, continuous state-and-action control systems.
result Any smooth, deterministic imitator policy suffers exponentially larger error than the expert.

Transformers learn to make decisions in new contexts from offline data.

problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.

In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in some cases. In this paper, we consider active imitation learning with the goal of…

2012-10-16abs ↗pdf ↗

The paper proposes a method to explain expert decisions by modeling preferences with 'what if' outcomes.

problem Interpreting and auditing decision-making policies in institutions.
method Integrating counterfactual reasoning into batch inverse reinforcement learning.
result The method effectively recovers accurate and interpretable descriptions of expert behavior.

It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The methods based on reinforcement learning, such as inverse reinforcement l…

2020-01-19abs ↗pdf ↗

Paper optimizes GAIL for online and offline learning with linear approximations.

problem Imitation learning from expert demonstrations with linear function approximations.
method Proposes optimistic and pessimistic algorithms for online and offline settings.
result Proves optimality and efficiency of proposed algorithms.

Interactive learning with hindsight instruction feedback achieves better performance than traditional methods.

problem Learning with expert supervision of optimal responses is often impractical or requires expert knowledge.
method Study of interactive learning with hindsight instruction feedback, introducing LORIL algorithm.
result LORIL algorithm achieves T\sqrt{T} regret, improving over baselines in domains with low-rank instruction-response distribution.

Paper proposes interpretable RL policies from a mixture of experts.

problem Making RL policies transparent and understandable in real-world applications.
method Policy iteration scheme with interpretable experts and prototypical states.
result Proposed algorithm learns policies comparable to neural networks but more interpretable.

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study…

2019-12-12abs ↗pdf ↗

We consider the problem of learning to behave optimally in a Markov Decision Process when a reward function is not specified, but instead we have access to a set of demonstrators of varying performance. We assume the demonstrators are classified into one of k ranks, and use ideas from ordinal regression to find a rewar…

2019-07-31abs ↗pdf ↗

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploratio…

2019-06-21abs ↗pdf ↗

Paper explores limits of imitation learning in MDPs, setting new suboptimality bounds.

problem Understanding the statistical limits of imitation learning in MDPs.
method Analyzes minimax statistical limits in two settings: pre-interaction and interaction.
result Establishes suboptimality bounds for imitation learning in MDPs, showing improvements with knowledge of transition.

New findings explain why online methods outperform offline methods in noisy expert feedback settings.

problem The challenge of learning from imperfect expert feedback in sequential decision-making systems.
method Introduced a noisy expert model and a novel variant of on-policy distillation (OPD) to address the gap between offline and online imitation learning.
result Online interaction with a noisy expert via OPD enables polynomial dependence on the horizon, unlike offline methods which require exponential growth in sample complexity.

Improved text-conditioned regression using LLMs and diffusion-based neural processes.

problem Major error cascades and computational inefficiency in LLMs for short sequences.
method Combining LLM predictive densities with a diffusion-based neural process.
result Better-calibrated predictions and locally consistent trajectories.

Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but doesn't achieve peak performance due to its inherent iid assumption about the st…

2020-01-21abs ↗pdf ↗

The paper teaches robots to navigate by learning costs from expert demonstrations.

problem Teaching robots to navigate autonomously using only expert observations.
method Developed a map encoder and cost encoder to infer semantic class probabilities and a cost function from expert observations.
result Robots can learn to follow traffic rules in a simulator using only semantic observations.

Novel framework learns policies from noisy expert demonstrations.

problem Learning effective policies with noisy expert demonstrations.
method Adaptive learning framework that jointly interacts with the environment and expert demonstrations, assigning weights to filter out noisy demonstrations.
result The proposed approach learns robustly with noisy demonstrations and achieves higher performance in fewer iterations.

This study compares 6 imitation learning algorithms using a common dataset and hyperparameter budget.

problem Difficulty in comparing different imitation learning algorithms due to varying datasets, base RL algorithms, and evaluation settings.
method Reimplemented and updated 6 different imitation learning algorithms, using a common off-policy algorithm (SAC) and a widely-used dataset (D4RL). Evaluated on a range of expert trajectories.
result GAIL consistently performs well across different sample sizes, while AdRIL performs well with one important hyperparameter to tune and behavioral cloning remains a strong baseline when data is plentiful.

Develops statistical framework for resolving reward function ambiguity in inverse reinforcement learning.

problem Non-uniqueness of reward functions in inverse reinforcement learning.
method Entropy regularization combined with least-squares reconstruction of the reward from the soft Bellman residual.
result Least-squares reward function is unique and consistent with the expert policy.

BALLAST optimizes Lagrangian observer placement for ocean vector fields.

problem Optimizing Lagrangian observer placement for time-dependent ocean vector fields.
method Bayesian active learning with look-ahead amendment for sea-drifter trajectories using a physics-informed spatio-temporal Gaussian process surrogate model.
result Noticeable benefits of BALLAST-aided observer placement strategies on synthetic and high-fidelity ocean models.

Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.

problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.

DO-IQS recovers optimal stopping region from expert trajectories, addressing specific challenges.

problem Recovering optimal stopping region from expert trajectories with unknown gain functions.
method Dynamics-Aware Offline Inverse Q-Learning incorporating temporal information and confidence-based oversampling.
result Demonstrated performance on real and artificial data, including optimal intervention for critical events.