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.

169,051 papers · 148 categories

Trend · papers per month

5.2%10.5%15.7%21.0% · Jun 201919922001200920172026
48 results for Experience Prioritization

A new method prioritizes and recycles experiences for better reinforcement learning.

problem Improving reinforcement learning efficiency by prioritizing and recycling experiences.
method Double-prioritized state-recycled (DPSR) experience replay.
result DPSR achieved state-of-the-art results in Atari games, outperforming original and prioritized methods.

In Hindsight Experience Replay (HER), a reinforcement learning agent is trained by treating whatever it has achieved as virtual goals. However, in previous work, the experience was replayed at random, without considering which episode might be the most valuable for learning. In this paper, we develop an energy-based fr…

2018-10-02abs ↗pdf ↗

This work improves MARL exploration efficiency using predictive guidance and prioritized experience replay.

problem Challenges in multi-agent reinforcement learning, especially in exploration efficiency and reward informativeness.
method A predictive network forecasts reward, guiding MARL to accelerate exploration. Improved prioritized experience replay utilizes TD error effectively.
result The proposed algorithm outperforms existing methods in cooperative multi-agent environments.

Experience replay is a key technique behind many recent advances in deep reinforcement learning. Allowing the agent to learn from earlier memories can speed up learning and break undesirable temporal correlations. Despite its wide-spread application, very little is understood about the properties of experience replay. …

2017-10-18abs ↗pdf ↗

New loss function equivalence reveals PER's uniform sampling can be improved.

problem Improving Prioritized Experience Replay (PER) for better learning efficiency.
method Transforming non-uniformly sampled data loss functions into uniformly sampled ones.
result Some environments can replace PER with a new loss function without performance loss.

Unified framework improves gene prioritization in disease studies.

problem Identifying genes involved in diseases using heterogeneous biological data.
method Network propagation-based gene prioritization with integrated biological information.
result Significant improvements in prioritizing genes not identified by traditional methods.

Curious Replay improves model-based reinforcement learning agents' adaptability.

problem Existing model-based reinforcement learning agents struggle to adapt quickly to changing environments.
method Curious Replay uses a curiosity-based priority signal for prioritized experience replay tailored to model-based agents.
result Agents using Curious Replay achieve improved performance in exploration and on benchmarks.

This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…

2018-05-15abs ↗pdf ↗

RATE metrics evaluate treatment prioritization rules, subsuming existing methods.

problem Comparing and testing the quality of treatment prioritization rules.
method Rank-weighted average treatment effect (RATE) metrics.
result RATE metrics enable asymptotically exact inference in various study settings.

A novel RL objective and prioritization framework improve performance and sample-efficiency in multi-goal tasks.

problem Learning diverse goals in multi-goal reinforcement learning.
method Maximum entropy regularization for objective and prioritization framework.
result Promising improvements in performance and sample-efficiency on multi-goal robotic tasks.

A new method reduces compounding errors in model-based reinforcement learning.

problem Compounding errors in long horizon predictions from model-based reinforcement learning.
method Maximum Entropy Model Rollouts (MEMR) with non-uniform sampling and prioritized experience replay.
result Significantly reduces computation requirements compared to other model-based methods.

Most exact methods for k-nearest neighbour search suffer from the curse of dimensionality; that is, their query times exhibit exponential dependence on either the ambient or the intrinsic dimensionality. Dynamic Continuous Indexing (DCI) offers a promising way of circumventing the curse and successfully reduces the dep…

2017-03-01abs ↗pdf ↗

Combines experience replay and exploration for better agent performance.

problem Improving exploration efficiency and robustness in reinforcement learning.
method Integrates Intrinsic Rewards with Prioritized Oversampled Experience Replay (POER).
result Achieves better agent performance and sample efficiency compared to PPO/RND.

A framework uses proxies to prioritize treatment without estimating causal effects.

problem Prioritizing treatment when causal effects are hard to estimate.
method Decision-focused framework identifying conditions for proxy usefulness.
result Proxies can recover correct effect ordering under specific conditions.

New algorithm learns efficiently in multi-agent settings.

problem Efficient learning in multi-agent Markov decision processes.
method Cooperative Prioritized Sweeping: model-based reinforcement learning with sample efficiency.
result Outperforms state-of-the-art on SysAdmin and randomized environments.

A new approach to cost-sensitive multiclass classification prioritizes certain classes over others.

problem Cost-sensitive multiclass classification where some classes are more important than others.
method Apportioned margin framework that shifts the decision boundary to prioritize certain classes.
result The method improves the error rate for important classes while reducing overall error.

Introduces PIT-plot for prioritizing projects based on their impact.

problem Optimizing R&D investments in project portfolios.
method Develops a new tool (PIT-plot) focusing on project impact rather than project properties.
result Identifies projects with the largest impact for risk mitigation or value-adding.

Optimizes reinforcement learning by prioritizing sets of samples over individual ones.

problem Limits exploration and improvement on harder examples due to focusing on isolated samples.
method Proposes Pass@K Policy Optimization (PKPO) to optimize for sets of samples that maximize reward when considered jointly.
result Optimization with novel low variance unbiased estimators for pass@k and its gradient leads to significant pass@k gains.

Enhances Federated Learning by prioritizing device contributions and adjusting aggregation parameters.

problem Data privacy and security in distributed learning systems.
method Integrates multiple criteria for device contribution, uses prioritized aggregation, and adapts aggregation parameters online.
result The proposed approach outperforms standard Federated Learning methods in distributed learning tasks.

CCLF improves sample efficiency in RL by prioritizing informative samples.

problem Learning from high-dimensional observations is challenging and unstable.
method Contrastive-Curiosity-Driven Learning Framework (CCLF) that prioritizes informative samples.
result CCLF improves sample efficiency and learning performance in RL.

This paper explores how balancing and filtering techniques affect predictive multiplicity in machine learning models.

problem Predictive multiplicity due to Rashomon effect in high-stakes environments.
method Investigates the impact of balancing and filtering techniques on predictive multiplicity using 21 real-world datasets.
result Data-centric AI strategies can mitigate predictive multiplicity, but preprocessing methods may introduce it.

Heteroskedasticity biases uplift model rankings, leading to inefficient treatment allocation.

problem Bias in uplift model rankings due to heteroskedasticity.
method Theoretical analysis and simulation on real-world data.
result Heteroskedasticity can cause individuals with high treatment effects to be ranked at the bottom, leading to inefficient treatment allocation.

SAEs struggle with feature consistency across runs, hindering MI reliability.

problem Inconsistency of learned SAE features across different training runs.
method Propose using the Pairwise Dictionary Mean Correlation Coefficient (PW-MCC) to measure feature consistency.
result High levels of feature consistency (0.80 for TopK SAEs on LLM activations) are achievable with appropriate architectural choices.

This work adopts the very successful distributional perspective on reinforcement learning and adapts it to the continuous control setting. We combine this within a distributed framework for off-policy learning in order to develop what we call the Distributed Distributional Deep Deterministic Policy Gradient algorithm, …

2018-04-23abs ↗pdf ↗

A new framework designs experiments for better decision-making.

problem Suboptimal experimental designs for downstream decision-making.
method Amortized decision-aware Bayesian Experimental Design (BED) with Transformer Neural Decision Process (TNDP).
result TNDP effectively designs experiments and facilitates accurate decision-making.

This paper improves self-play learning in games by manipulating experience distributions.

problem Improving self-play learning in games through better experience sampling.
method Three approaches: weighted sampling, Prioritized Experience Replay, and diversifying trajectories.
result Major improvements in early training performance in some games, minor improvements overall.

Deep neural networks (DNNs) are increasingly being adopted for sensing and control functions in a variety of safety and mission-critical systems such as self-driving cars, autonomous air vehicles, medical diagnostics, and industrial robotics. Failures of such systems can lead to loss of life or property, which necessit…

2019-01-11abs ↗pdf ↗

A new network learns to prioritize messages for efficient multi-robot path planning.

problem Efficient path planning and coordination for large-scale multi-robot systems.
method Message-Aware Graph Attention Network (MAGAT) incorporating attention mechanisms.
result MAGAT achieves performance close to a coupled centralized expert algorithm.

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differen…

2017-06-16abs ↗pdf ↗

Designs for allocating resources to prioritize needy applicants while estimating treatment effects.

problem Resource allocation under uncertainty with prioritized queues.
method Priority-queue randomization for treatment assignment and estimation of treatment effects.
result Identification of causal effects under different arrival and treatment assignment scenarios.

Traditional medicine typically applies one-size-fits-all treatment for the entire patient population whereas precision medicine develops tailored treatment schemes for different patient subgroups. The fact that some factors may be more significant for a specific patient subgroup motivates clinicians and medical researc…

2017-09-26abs ↗pdf ↗