The AlphaZero algorithm for the learning of strategy games via self-play, which has produced superhuman ability in the games of Go, chess, and shogi, uses a quantitative reward function for game outcomes, requiring the users of the algorithm to explicitly balance different components of the reward against each other, s…
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
48 results for “reward modification”
Algorithm reduces regret in multi-player bandits with unknown collision rewards.
problem Reducing regret in multi-player multi-armed bandits with unknown collision rewards.
method Proposes an algorithm that combines a modified successive elimination strategy with a communication protocol to estimate suboptimality gaps and coordinate among players.
result Achieves logarithmic regret for the problem when collision reward is unknown.
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
Adapts two algorithms for online learning with delayed rewards.
problem Online learning with delayed rewards in generalized linear contextual bandits.
method Modifies upper confidence bounds and Thompson sampling algorithms for delayed rewards.
result Both algorithms can be made robust to delays, improving their performance.
The paper tackles non-cumulative objectives in reinforcement learning and proposes modifications to existing algorithms.
problem Optimizing objectives that are not naturally expressed as summations of rewards in various fields.
method The paper modifies the Bellman optimality equation to handle non-cumulative objectives by replacing summation with a generalized operation.
result The modified Bellman updates can converge to the globally optimal solution under certain conditions.
Two new algorithms optimize rewards while respecting safety constraints in sequential decisions.
problem Optimizing rewards with safety constraints in sequential decisions.
method Stage-wise conservative linear Thompson Sampling (SCLTS) and stage-wise conservative linear UCB (SCLUCB).
result Probabilistic regret bounds of order O(\sqrt{T} \log^{3/2}T) and O(\sqrt{T} \log T).
A new method optimizes in nonstationary environments with many arms efficiently.
problem Optimizing in nonstationary environments with a large number of arms.
method Gaussian interpolation to learn continuous Lipschitz reward functions in nonstationary environments.
result Efficiently learns continuous Lipschitz reward functions with cumulative regret.
We use a novel modification of Multi-Armed Bandits to create a new model for recommendation systems. We model the recommendation system as a bandit seeking to maximize reward by pulling on arms with unknown rewards. The catch however is that this bandit can only access these arms through an unreliable intermediate that…
This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumenta…
In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and…
In this paper, we derive a new model of synaptic plasticity, based on recent algorithms for reinforcement learning (in which an agent attempts to learn appropriate actions to maximize its long-term average reward). We show that these direct reinforcement learning algorithms also give locally optimal performance for the…
This paper explores how environmental properties can simplify reinforcement learning in non-episodic settings.
problem Challenges in reinforcement learning with continuous interaction and sparse delayed rewards.
method Analysis of environment shaping and dynamism properties to simplify learning.
result Properties like environment shaping and dynamism can significantly ease learning in non-episodic, sparse reward settings.
A new method for reinforcement learning that adapts to different domains using auxiliary classifiers.
problem Training reinforcement learning agents to perform well in different domains with varying dynamics.
method Learning auxiliary classifiers to distinguish source-domain from target-domain transitions and modifying the reward function accordingly.
result The approach improves transfer performance in reinforcement learning tasks with varying dynamics.
UCRL3 improves UCRL2's efficiency in reinforcement learning by reducing exploration.
problem Long burn-in phases in numerical experiments of UCRL2.
method UCRL3 uses state-of-the-art time-uniform concentration inequalities and adaptive support computation to tighten exploration.
result UCRL3 achieves a better numerical improvement over UCRL2 in standard environments.
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep reinforcement learning (DRL) agents and can be exploited by an adversary with access to…
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…
New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.
In this paper we build on previous work which uses inferences techniques, in particular Markov Chain Monte Carlo (MCMC) methods, to solve parameterized control problems. We propose a number of modifications in order to make this approach more practical in general, higher-dimensional spaces. We first introduce a new tar…
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and pre…
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement lea…
A new framework for offline RL improves policy flexibility and regularity.
problem Lack of environmental interactions in offline RL leads to poor policy performance.
method Proposes a behavior-regularized implicit policy framework with modified policy-matching methods.
result The framework improves policy effectiveness and robustness beyond static datasets.
Paper tackles non-stationary kernelized bandits with near-optimal algorithm.
problem Minimizing regret in a time-varying reward function.
method Near-optimal algorithm with a novel restarting phased elimination with random permutation (R-PERP).
result Regret upper bound matches the lower bound, making the algorithm near-optimal.
A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.
problem Determining if the root node value of a tree is at least a given threshold.
method Developed a δ-correct sequential sampling algorithm based on the Track-and-Stop strategy.
result Ratio-based modification of D-Tracking strategy reduces sample complexity and computational cost.
Factored Banditscs.LG
We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special case, but significantly relax the assumptions on the form of the reward function…
Improved stochastic Halpern iteration for fixed-point approximation in normed spaces.
problem Approximating fixed-points of nonexpansive and contractive operators in normed finite-dimensional spaces.
method Stochastic Halpern iteration with minibatch, analyzing oracle complexity.
result Improved oracle complexity for nonexpansive operators, with a lower bound of .
We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and …
A scheme robust to action erasures improves MAB performance.
problem Learning in multi-arm bandits with erasure channels.
method Proposes a scheme to work on top of any MAB algorithm.
result Worst-case regret is at most a factor of away from no-erasure case.
Paper analyzes TD() convergence rates for arbitrary features.
problem Convergence rates for linear TD() under arbitrary features.
method Developed a novel stochastic approximation result for arbitrary features.
result Established convergence rates for linear TD() without linearly independent features assumption.
This work improves testing of machine learning model modifications using novel statistical methods.
problem Overfitting and conservative Bonferroni correction when testing multiple model modifications.
method Introduces alpha-recycling and SRGPs to control error rate and approve more beneficial modifications.
result Novel statistical methods approve a higher number of beneficial modifications than previous approaches.
Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level …
Machine learning is often used in competitive scenarios: Participants learn and fit static models, and those models compete in a shared platform. The common assumption is that in order to win a competition one has to have the best predictive model, i.e., the model with the smallest out-sample error. Is that necessarily…
New method extends low-rank MDPs to continuous action spaces.
problem Limited applicability of current low-rank MDP methods to continuous action spaces.
method Extending FLAMBE algorithm to continuous action spaces with Hölder smoothness conditions.
result Similar PAC bound achieved for continuous actions with polynomial dependence on smoothness order.
Meta-agent learns effective exploration from offline data.
problem Design a meta-agent to quickly maximize reward in unseen tasks.
method Bayesian RL approach with adaptive neural belief estimate.
result Meta-agent learns effective exploration behavior from diverse tasks.
New method detects RNA modifications without prior training, revealing novel sites.
problem Detecting RNA modifications with high accuracy and sensitivity.
method Anomaly detection using nanopore raw ionic current signals and nearest neighbor comparison.
result Detects diverse RNA modifications without prior training, including a novel 2'-O-methylated site in DENV.
Truthful Self-Playstat.ML
Framework improves self-play for cooperative multi-agent learning.
problem Evolutionary learning converges to bad local optima in multi-agent RL.
method Add imaginary rewards using peer prediction method to elicit truthful signals.
result State-of-the-art performance in predator prey, traffic junction and StarCraft tasks.
Reinforcement Learning in domains with sparse rewards is a difficult problem, and a large part of the training process is often spent searching the state space in a more or less random fashion for any learning signals. For control problems, we often have some controller readily available which might be suboptimal but n…
We define an operation on homology which we call an -twist annulus modification. We give a new construction of smoothly slice knots and exotically slice knots via -twist annulus modifications. As an application, we present a new example of a smoothly slice knot with non-slice derivatives. Such examples we…
Improved POMDP regret to sqrt(T) with known observation model.
problem Average-reward POMDPs with unknown transition model but known observation model.
method Optimistic algorithm using deterministic policies and novel estimation techniques.
result First approach with regret guarantee of sqrt(T) against optimal policy.
We present an approach to make molecular optimization more efficient. We infer a hypergraph replacement grammar from the ChEMBL database, count the frequencies of particular rules being used to expand particular nonterminals in other rules, and use these as conditional priors for the policy model. Simulating random mol…
Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real-world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation-driven methods such as Adaptive Stress Testing (AST) have b…
A modification of the confidence screening mechanism based on adaptive weighing of every training instance at each cascade level of the Deep Forest is proposed. The idea underlying the modification is very simple and stems from the confidence screening mechanism idea proposed by Pang et al. to simplify the Deep Forest …
Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact with the other agents that have fixed policies. Modeling the behavior of other …
Proposes simplified SHAP for faster black-box model explanations.
problem Computational expense of SHAP for models with many features.
method Ensemble of random SHAPs with feature selection and point generation.
result Efficiency and properties demonstrated through numerical experiments.
Optimism stabilizes Thompson Sampling for adaptive inference in multi-armed bandits.
problem Subtle inferential properties of Thompson Sampling under adaptive data collection.
method Introduced optimism as a key mechanism to restore stability and validity of inference.
result Suitably implemented optimism stabilizes Thompson Sampling and enables asymptotically valid Wald inference.
Behavior modification improves prediction accuracy by nudging user behavior.
problem Improving prediction accuracy using behavior modification techniques.
method Combining prediction and behavior modification with reinforcement learning algorithms.
result Behavior modification can make predictions more certain but may not generalize.
Study of unimodular Sasaki and Vaisman Lie groups, determining all modifications explicitly.
problem Classifying unimodular Sasaki and Vaisman Lie groups.
method Applying the technique of modification to determine all homogeneous Sasaki and Vaisman manifolds of unimodular Lie groups explicitly.
result Complete classification of unimodular Sasaki and Vaisman Lie groups.
We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the…
We study large-scale classification problems in changing environments where a small part of the dataset is modified, and the effect of the data modification must be quickly incorporated into the classifier. When the entire dataset is large, even if the amount of the data modification is fairly small, the computational …