Dealing with sparse rewards is a longstanding challenge in reinforcement learning. The recent use of hindsight methods have achieved success on a variety of sparse-reward tasks, but they fail on complex tasks such as stacking multiple blocks with a robot arm in simulation. Curiosity-driven exploration using the predict…
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 “block rewards”
We decode latent states in Block MDPs and learn near-optimal policies.
problem Model estimation and reward-free learning in Block MDPs.
method Information-theoretical lower bound and efficient model estimation algorithm.
result Our algorithm approaches the information-theoretical limit for latent state decoding and converges to optimal policies.
Mind the Gap in the Mining Gameq-fin.GN
Game-theoretic analysis of mining gaps in blockchain systems.
problem Strategic mining behavior and its impact on blockchain stability.
method Game-theoretic model and Nash equilibrium analysis.
result Mining gaps can destabilize blockchain systems, especially with decreasing block rewards.
A novel bandit problem with context-dependent rewards and blocking.
problem Contextual bandit problem with blocking.
method Online bipartite matching, UCB algorithm, delayed exploitation, opportunistic subsampling.
result Guaranteed -regret in bandit setting.
Algorithm maximizes user rewards under per-item budget constraints.
problem Maximizing cumulative rewards in collaborative bandits with budget constraints.
method Collaborative algorithm B-LATTICE that clusters users and collaborates across groups.
result Achieves sub-linear regret bounds matching minimax bounds.
Unified approach for non-stationary linear bandits with dynamic regret.
problem Non-stationary linear bandits with round-specific feasible actions and drifting reward models.
method Unified misspecification-reduction viewpoint, restarting algorithms with misspecification-dependent regret guarantees.
result Optimal \(T^{2/3}P_T^{1/3}\) dynamic-regret dependence for both linear bandits and contextual linear bandits.
PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
Enhances portfolio performance using deep reinforcement learning and future rewards.
problem Improving existing high-performing portfolio strategies through dynamic rebalancing.
method Proximal Policy Optimization (PPO) and Oracle agents for dynamic rebalancing; Regret-based Sharpe reward function; Transaction cost scheduler; Future-looking reward function; Circular block bootstrap training.
result Significantly enhanced portfolio performance compared to traditional strategies and baselines.
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 …
Blocking Banditscs.LG
We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusing an arm too often is undesirable (e.g. making the same product recommendation repeatedly) or infeasible (e.g. compute job scheduling on ma…
Training-free method improves large language model sequence quality via reward-guided sampling.
problem Optimizing large language model sequence quality over token likelihood.
method Reward-augmented target distribution combined with Sequential Monte Carlo sampling.
result Significant gains in sequence generation and mathematical reasoning tasks.
Two algorithms tackle heavy-tailed rewards in reinforcement learning with linear function approximation.
problem Online sequential decision-making with heavy-tailed rewards.
method AdaOFUL and VARA algorithms for linear stochastic bandits and MDPs, using modified adaptive Huber regression.
result Achieved state-of-the-art and variance-aware regret bounds for heavy-tailed rewards.
Meta-learning curiosity algorithms improves exploration across various tasks.
problem Generating curious behavior in reinforcement learning.
method Meta-learning approach to adapt reward signals dynamically.
result Two novel curiosity algorithms outperform human-designed ones.
Investigates risk measures for DC pension decumulation.
problem Develop optimal decumulation strategies for DC plan holders.
method Formulates decumulation as a control problem, studies risk measures (expected shortfall, linear shortfall, probability of shortfall).
result Optimal controls for expected reward and expected shortfall are identical to those for expected reward and linear shortfall.
The focal point of this paper is the issue of "drawdown" which arises in recursive betting scenarios and related applications in the stock market. Roughly speaking, drawdown is understood to mean drops in wealth over time from peaks to subsequent lows. Motivated by the fact that this issue is of paramount concern to co…
Nonparametric Thompson Sampling achieves optimal regret for risk-averse bandits with sub-Gaussian rewards.
problem Optimizing risk-averse bandit problems with sub-Gaussian rewards.
method Anchor-free nonparametric Thompson Sampling algorithm .
result Achieves regret matching the instance-dependent lower bound to leading order in .
New -Coverage objective simplifies exploration in reinforcement learning.
problem Challenges in exploration for high-dimensional domains.
method Introduces -Coverage objective to enable efficient exploration and planning.
result First computationally efficient algorithms for online reinforcement learning with low coverability.
This paper optimizes slate decision systems for large action spaces.
problem Optimizing large-scale decision systems with arbitrary reward functions.
method A policy optimization framework with a novel relaxation of decision functions.
result Demonstrates the effectiveness of the proposed method on large action spaces.
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.
We propose combinatorial cascading bandits, a class of partial monitoring problems where at each step a learning agent chooses a tuple of ground items subject to constraints and receives a reward if and only if the weights of all chosen items are one. The weights of the items are binary, stochastic, and drawn independe…
Ethereum transition to PoS reduces energy consumption and decentralizes the network.
problem Transitioning from proof-of-work to proof-of-stake to reduce energy consumption and decentralize the network.
method Analyzed the impact of the Ethereum transition to proof-of-stake on network performance, competing platforms, and transaction fees.
result The transition to PoS has reduced energy consumption by 99.98% and decreased network concentration.
Quantum Proof-of-Work uses boson sampling to secure blockchain consensus.
problem Ensuring secure and efficient blockchain consensus.
method Proposes using quantum boson sampling as a Proof-of-Work scheme for blockchain.
result Demonstrates a robust and energy-efficient PoW scheme.
Theoretical analysis shows LLMs can self-correct responses through in-context learning.
problem Understanding how large language models improve through self-correction.
method Theoretical analysis based on simplified alignment task, focusing on softmax attention, multi-head attention, and MLP blocks.
result LLMs can refine responses in an in-context way when given accurate self-examinations as rewards.
Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model pre…
This paper presents a novel Block Iterative Bayesian Algorithm (Block-IBA) for reconstructing block-sparse signals with unknown block structures. Unlike the existing algorithms for block sparse signal recovery which assume the cluster structure of the nonzero elements of the unknown signal to be independent and identic…
This letter presents a novel Block Bayesian Hypothesis Testing Algorithm (Block-BHTA) for reconstructing block sparse signals with unknown block structures. The Block-BHTA comprises the detection and recovery of the supports, and the estimation of the amplitudes of the block sparse signal. The support detection and rec…
Extension of SBL Algorithms for the Recovery of Block Sparse Signals with Intra-Block Correlationstat.ML
We examine the recovery of block sparse signals and extend the framework in two important directions; one by exploiting signals' intra-block correlation and the other by generalizing signals' block structure. We propose two families of algorithms based on the framework of block sparse Bayesian learning (BSBL). One fami…
We theoretically investigate the convergence rate and support consistency (i.e., correctly identifying the subset of non-zero coefficients in the large sample limit) of multiple kernel learning (MKL). We focus on MKL with block-l1 regularization (inducing sparse kernel combination), block-l2 regularization (inducing un…
There exist various types of network block models such as the Stochastic Block Model (SBM), the Degree Corrected Block Model (DCBM), and the Popularity Adjusted Block Model (PABM). While this leads to a variety of choices, the block models do not have a nested structure. In addition, there is a substantial jump in the …
SympFormer accelerates attention blocks using inertial dynamics on density spaces.
problem Improving the efficiency of self-attention blocks in Transformers.
method Introduced accelerated attention blocks derived from inertial Nesterov dynamics on density spaces.
result Accelerated attention blocks converge faster than classical blocks while preserving oracle calls.
We introduce block-tree graphs as a framework for deriving efficient algorithms on graphical models. We define block-tree graphs as a tree-structured graph where each node is a cluster of nodes such that the clusters in the graph are disjoint. This differs from junction-trees, where two clusters connected by an edge al…
We simplify matrix computations for block matrices, especially useful for covariance and correlation matrices.
problem Complex computations for block matrices, especially for covariance and correlation matrices.
method Obtained a canonical representation for block matrices, facilitating computation of various matrix operations.
result Simplified computation of matrix operations for block matrices, particularly useful for covariance and correlation matrices.
Attention mechanism is a hot spot in deep learning field. Using channel attention model is an effective method for improving the performance of the convolutional neural network. Squeeze-and-Excitation block takes advantage of the channel dependence, selectively emphasizing the important channels and compressing the rel…
Proposes BMME for optimizing nonsmooth nonconvex problems with block structure.
problem Optimizing nonsmooth nonconvex problems with block structure.
method Block Alternating Bregman Majorization Minimization with Extrapolation (BMME).
result Subsequential convergence to a first-order stationary point under mild assumptions, global convergence under stronger conditions.
Alternating Direction Method of Multipliers (ADMM) has become a widely used optimization method for convex problems, particularly in the context of data mining in which large optimization problems are often encountered. ADMM has several desirable properties, including the ability to decompose large problems into smalle…
Paper proposes ABDR for convex subspace clustering with adaptive block diagonal representation.
problem Subspace clustering with block diagonal structure for noisy data.
method ABDR explicitly pursues block diagonality without sacrificing convexity, using a specially designed convex regularizer.
result Experimental results show ABDR outperforms state-of-the-arts.
Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.
problem Reward hacking in RL models exploiting reward misspecifications.
method Constructed four RL environments with misspecified rewards; analyzed agent capabilities and behavior.
result More capable agents exploit reward misspecifications, achieving higher proxy reward but lower true reward.
New algorithms reduce bias in federated learning for non-i.i.d. data.
problem Client and block biases in federated learning with non-i.i.d. data.
method Multi-model parallel SGD (MM-PSGD) and multi-chain parallel SGD (MC-PSGD) algorithms.
result Achieve a linear speedup with convergence rate .
In the present paper we study a sparse stochastic network enabled with a block structure. The popular Stochastic Block Model (SBM) and the Degree Corrected Block Model (DCBM) address sparsity by placing an upper bound on the maximum probability of connections between any pair of nodes. As a result, sparsity describes o…
Incorporating deep neural networks in image compressive sensing (CS) receives intensive attentions in multimedia technology and applications recently. As deep network approaches learn the inverse mapping directly from the CS measurements, the reconstruction speed is significantly faster than the conventional CS algorit…
Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.
problem Lack of structured representation for non-Markovian stochastic rewards in reinforcement learning.
method Introduces probabilistic reward machines (PRMs) and presents an algorithm to learn them from decision processes.
result Algorithm proves correct and convergent for learning PRMs from decision processes.
This work analyzes the value of future reward information in RL.
problem Analyzing the impact of knowing future rewards in reinforcement learning.
method Competitive analysis and worst-case reward distribution.
result Exact ratios between standard RL agents and those with future-reward lookahead.
Self-supervised reward prediction improves RL in sparse reward settings.
problem Data efficiency and sparse reward signals in reinforcement learning.
method Learning a state representation for reward prediction and using it to shape rewards.
result Self-supervised reward prediction enhances RL algorithms in single-goal environments.
The study categorizes reward errors in reinforcement learning, finding some can be beneficial.
problem Training language models with imperfect proxy rewards.
method Theoretical analysis of policy gradient optimization and categorization of reward errors.
result Reward errors can be benign or even beneficial, preventing policy from stalling.
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
New formula calculates loss from arbitrage in blockchain liquidity pools.
problem Calculating loss from arbitrage in Automated Market Makers (AMMs) under varying block times.
method Derived a closed-form approximation for expected loss using random walk theory.
result The formula approximates the loss from arbitrage with high accuracy and shows that constant block intervals minimize this loss.
Reward models need more than just accuracy for effective RLHF.
problem The effectiveness of reward models in RLHF is not fully understood.
method An optimization perspective to evaluate reward models.
result Reward models with low reward variance can lead to a flat optimization landscape, hindering performance.
This paper solves matrix blind joint block diagonalization with noise.
problem Identifying the diagonalizer and block diagonal structure of matrices under noise.
method Bi-block diagonalization method.
result The method can identify the exact solution under certain conditions.