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.

168,695 papers · 148 categories

Trend · papers per month

144288432576 · Jun 202019922001200920172026
48 results for Final Adaptation RL

Reward-poisoning attacks can force RL agents to learn bad policies, and we categorize and quantify their feasibility.

problem Reward-poisoning attacks can manipulate RL agents to learn undesirable policies.
method Categorize attacks by infinity-norm constraint, provide thresholds for feasibility, and develop adaptive attack strategies.
result Adaptive reward-poisoning attacks can achieve the nefarious policy in polynomial steps, while non-adaptive attacks require exponential steps.

Gradient-based meta-RL fails with incorrect task distributions, leading to instability and poor performance.

problem Gradient-based meta-RL's sensitivity to task distributions causes instability and poor performance.
method Proposes meta Active Domain Randomization (meta-ADR) to learn task distributions for gradient-based meta-RL.
result Meta-ADR improves stability and generalization of MAML on simulated locomotion and navigation tasks.

A common problem in Machine Learning and statistics consists in detecting whether the current sample in a stream of data belongs to the same distribution as previous ones, is an isolated outlier or inaugurates a new distribution of data. We present a hierarchical Bayesian algorithm that aims at learning a time-specific…

2018-05-15abs ↗pdf ↗

Selective state-adaptive regularization improves offline RL performance.

problem Extrapolation errors and value overestimation in static dataset RL.
method State-adaptive regularization coefficients trust Bellman-driven results selectively.
result Significant improvement in performance on D4RL benchmark.

When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a significant effect on an agent's performance, however, and determining a suitable approximation arch…

2017-03-23abs ↗pdf ↗

evo-RL combines evolutionary computation with reinforcement learning for better adaptability.

problem Improving reinforcement learning algorithms' adaptability and performance in environments with rewardless states.
method Embedding reinforcement learning in an evolutionary cycle, distinguishing instinctive from learnable behavior.
result evo-RL leads to state-of-the-art performance on OpenAI Gym control problems with rewardless states.

Pre-trained LLM adapted with LoRA improves offline RL for quantitative trading.

problem Challenges in offline RL for quantitative trading due to complex temporal dependencies and overfitting.
method Integrates pre-trained GPT-2 weights and LoRA for efficient fine-tuning of a Decision Transformer.
result Outperforms existing offline RL methods in certain trading scenarios.

ABO extends RLS for online learning in non-stationary time-series, improving accuracy and speed.

problem Online learning in non-stationary time-series with overparameterized models.
method QR-based exponentially weighted RLS algorithm with orthogonal-triangular updates.
result ABO maintains bounded residuals and stable condition numbers while achieving speed improvements.

FLAP adapts policies quickly to new tasks using shared linear representations.

problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.

Combines RL and BF for risk-managed portfolio optimization.

problem Risk management in RL-based portfolio optimization under high volatility.
method Integrates reinforcement learning with barrier functions for dynamic risk control.
result Demonstrates superior performance in real-world data compared to RL-only approaches.

Adaptive spectral RL method enhances RL performance and interpretability.

problem Balancing interpretability and performance in reinforcement learning.
method Spectral based linear RL approach with adaptive regularization.
result Near-optimal bounds for parameter estimation and generalization error.

Applying probabilistic models to reinforcement learning (RL) enables the application of powerful optimisation tools such as variational inference to RL. However, existing inference frameworks and their algorithms pose significant challenges for learning optimal policies, e.g., the absence of mode capturing behaviour in…

2018-11-03abs ↗pdf ↗

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…

2018-10-16abs ↗pdf ↗

This research tackles balancing exploration and exploitation in deep RL for partially observable systems.

problem Balancing exploration and exploitation in deep RL for partially observable systems.
method Deployed and tested several techniques including adaptive and deterministic exploration strategies, and a modified quadratic loss function.
result Adaptive methods better approximate the trade-off between exploration and exploitation.

This paper bridges offline and online RL by studying policy finetuning with a reference policy.

problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.

TDprop uses Jacobi preconditioning to improve adaptive optimizers in Deep RL.

problem Improving performance of adaptive optimizers in Deep RL.
method TDprop computes per-parameter learning rates based on Jacobi preconditioning of the TD update rule.
result TDprop matches or exceeds Adam's performance in Deep RL experiments, suggesting Jacobi preconditioning can improve adaptive methods.

SIBRE boosts reinforcement learning convergence by rewarding improvement over past performance.

problem Improving the rate of convergence in reinforcement learning.
method SIBRE is a reward shaping approach that rewards improvement over the agent's own past performance.
result SIBRE converges faster and more stably to the optimal policy compared to baseline RL algorithms.

Combines model-based and model-free RL for better financial market performance.

problem Challenges of Reinforcement Learning in volatile financial markets.
method Adapts model-based RL with model-free RL, incorporating contextual signals and walk-forward analysis.
result Outperforms traditional financial models in various metrics.

Reinforce-Ada improves RL for language models by adaptively sampling difficult prompts.

problem Signal loss in RL for large language models due to undersampling.
method Adaptive sampling based on a non-linear RL objective, optimizing prompt difficulty weighting.
result Reinforce-Ada significantly outperforms uniform sampling, recovering lost signals and accelerating convergence.

Empirical study shows consistent meta-RL algorithms adapt to OOD tasks.

problem Theoretical consistency of meta-RL algorithms and its practical implications.
method Empirical investigation of representative meta-RL algorithms, focusing on consistency and adaptation to out-of-distribution tasks.
result Theoretical consistent algorithms can adapt to OOD tasks, while inconsistent ones cannot, but can still fail for poor exploration.

IG-RL learns adaptive traffic signals for any network, outperforming existing methods.

problem Adaptive traffic signal control for large networks with combinatorial state and action spaces.
method Graph-Convolutional Networks for decentralized, flexible control.
result IG-RL generalizes to new networks and traffic conditions without additional training.

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…

2019-09-30abs ↗pdf ↗

SPAQL improves RL by adaptively partitioning state-action space and learning a time-invariant policy.

problem Efficient model-free reinforcement learning with scalable algorithms.
method Adaptive Q-learning with UCB and Boltzmann exploration, automatically tuning temperature.
result SPAQL converges faster and uses fewer resources than AQL, showing higher sample efficiency.

A new offline RL framework unifies imitation learning and vanilla offline RL.

problem Learning from expert datasets without active data collection.
method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.
result LCB algorithm achieves a faster rate of 1/N1/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range.

CUDC collects diverse data for offline RL by predicting future states.

problem Challenges in collecting task-agnostic data for offline RL.
method Adaptive temporal distances for curiosity-driven data collection.
result CUDC outperforms existing unsupervised methods in offline RL tasks.

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, …

2017-07-26abs ↗pdf ↗

Bayesian RL enhances LLMs to reflectively explore and correct errors.

problem LLMs trained via RL lack reflective behaviors like rethinking and error correction.
method Bayesian RL framework that optimizes expected return under posterior distribution over Markov decision processes.
result BARL algorithm improves LLM performance in reasoning tasks.