Adapts deep reinforcement learning to ordinal rewards.
problem Using numerical rewards in reinforcement learning has drawbacks; ordinal rewards offer an alternative.
method Develops a general approach to converting reinforcement learning algorithms to ordinal reward systems, including Ordinal Deep Q-Networks.
result Ordinal Deep Q-Networks perform comparably to numerical variants on engineered problems and better on simpler reward signals.
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD( λ λ λ ). result Improved numerical stability and broader step-size range.
New algorithm uses Whittle index to improve Q-learning for restless bandits.
problem Optimizing decision-making in multiarmed restless bandits with average reward.
method Introduces a novel reinforcement learning algorithm combining Q-learning and Whittle index policy.
result Demonstrates significant computational gains and excellent empirical performance.
Incentivized exploration improves MAB performance under reward drift.
problem Improving exploration in multi-armed bandits with biased feedback.
method Analysis of three MAB algorithms (UCB, ε-Greedy, Thompson Sampling) under drifted reward feedback.
result All algorithms achieve O ( log T ) \mathcal{O}(\log T) O ( log T ) regret and compensation under drifted reward. A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
New bandit algorithms improve sparse reward learning.
problem Sparse rewards hinder learning efficiency in real-world bandit applications.
method Developed algorithms based on Upper Confidence Bound and Thompson Sampling for zero-inflated distributions.
result Empirical performance of new algorithms is superior to existing methods.
Method predicts future rewards from past actions in a linear Gaussian system.
problem Maximizing cumulative reward in a stochastic multi-armed bandit with linear Gaussian dynamics.
method Proposes a method using a modified Kalman filter to predict future rewards based on past rewards.
result Reward from any action can be used to predict another action's future reward.
Unified framework improves diffusion model rewards without full trajectories.
problem Limited theoretical understanding of guided diffusion samplers.
method Developed a unified algorithmic and theoretical framework for diffusion guidance and reward-guided diffusion.
result Framework shows CFG decreases expected reciprocal of classifier probability.
Study tackles infinitely many-armed bandits with rotting rewards, achieving tight regret bounds.
problem Infinitely many-armed bandits with rotting rewards.
method Adaptive sliding window UCB algorithm for slow and abrupt rotting scenarios.
result Achieves tight regret bounds for both slow and abrupt rotting scenarios.
Unified framework for estimating reward functions in competitive games.
problem Estimating unknown reward functions in competitive games.
method Unified framework with entropy regularization for reward function recovery.
result Strong theoretical guarantees and practical effectiveness demonstrated.
This paper explores intrinsic rewards to improve learning from multiple value functions.
problem How to adapt reinforcement learning systems to optimize learning from multiple value functions.
method Investigated and compared 14 different intrinsic reward mechanisms in a new bandit-like parallel-learning testbed.
result Intrinsic rewards based on the amount of learning can generate useful behavior, if each individual learner is introspective.
The multi-armed bandit (MAB) problem is a classic example of the exploration-exploitation dilemma. It is concerned with maximising the total rewards for a gambler by sequentially pulling an arm from a multi-armed slot machine where each arm is associated with a reward distribution. In static MABs, the reward distributi…
This paper formalizes reward training in RLHF and provides theoretical guarantees.
problem Costly human feedback collection in RLHF.
method Linear contextual dueling bandit method for regret minimization.
result Derives bounds on simple regret for offline reward training.
The paper identifies all ε-optimal arms in a bandit problem with Gaussian rewards.
problem Identifying all ε-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards.
method The paper provides two lower bounds and a Track-and-Stop strategy to solve the problem, with an efficient numerical method to solve the convex max-min program.
result The Track-and-Stop strategy has asymptotically optimal average sample complexity in the regime of low risk.
Paper develops methods to optimize policies directly from human feedback without reward inference.
problem Challenges in RLHF, including reward model overfitting and distribution shift.
method Develops two algorithms for RLHF without reward inference, using zeroth-order gradient approximators.
result Establishes polynomial convergence rates and outperforms existing methods in numerical experiments.
Model shows how centralization occurs in cryptocurrency mining.
problem Centralization of reward and computational power in Bitcoin-like cryptocurrencies.
method Mean field game model to study miner competition and reward distribution.
result Heterogeneity of initial wealth leads to greater imbalance in reward distribution.
New approach to multi-armed bandit problem aims to maximize highest total reward.
problem Traditional multi-armed bandit problem objective of maximizing total reward is not suitable in certain applications.
method Adaptive explore-then-commit policy with confidence bounds and adaptive stopping criterion.
result Achieves asymptotic and worst-case regret bounds for the new objective.
Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) was recently proposed to tackle…
A new method learns policies from sub-optimal trajectories.
problem Reinforcement learning's brittleness and difficulty in tuning.
method Conditioning policies on the reward of sub-optimal trajectories.
result Effective policies can be learned without expert demonstrations.
A method to train multi-agent reinforcement learning models without intrinsic rewards.
problem Training multi-agent reinforcement learning models with sparse rewards is challenging.
method A learning-based exploration strategy using variational graph autoencoder to generate initial states.
result The method improves the training and performance of multi-agent reinforcement learning models.
New insights into balancing reward and fairness in stochastic MAB.
problem Balancing reward and fairness in stochastic multi-armed bandits.
method Formulated a penalization framework and proposed a hard-threshold UCB-like algorithm.
result Asymptotic fairness, nearly optimal regret, better reward-fairness tradeoff.
This paper extends the MAB problem to consider risk-reward tradeoffs.
problem Maximizing reward while accounting for risk in multi-armed bandit problems.
method Introduced the Risk Aware Lower Confidence Bound (RALCB) algorithm to solve the mean-variance MAB problem.
result The RALCB algorithm performs better than the algorithm in Sani et al. (2012) in both independent and dependent scenarios.
Study improves reinforcement learning for stable long-term performance.
problem Distributionally robust average-reward reinforcement learning for stable long-term performance.
method Proposes two algorithms to achieve near-optimal sample complexity.
result Achieves a sample complexity of O ( ∣ S ∣ ∣ A ∣ t m i x 2 ε − 2 ) O(|\mathbf{S}||\mathbf{A}| t_{\mathrm{mix}}^2\varepsilon^{-2}) O ( ∣ S ∣∣ A ∣ t mix 2 ε − 2 ) for estimating optimal policy and robust average reward. New algorithm reduces regret in multi-armed bandit problems with Gaussian rewards.
problem Optimizing decisions in multi-armed bandit problems with Gaussian rewards.
method Proposed TSCG and UTSCG algorithms using Thompson Sampling with Gaussian prior.
result Achieved lower regret bounds for optimal arm selection.
Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.
problem Nonstationary environment with changing base arms' distributions and causal relationships.
method Upper Confidence Bound (UCB) algorithm with change-point detector and group restart strategy.
result Regret upper bound reflecting effects of structural and distribution changes.
This study proposes hidden state curiosity to enhance RL models' resilience against noise.
problem Curiosity traps in RL models distract agents from discovering novel experiences.
method Proposed hidden state curiosity based on the Free Energy Principle to reward agents for KL divergence between predictive priors and posteriors.
result Agents with hidden state curiosity are more resilient against curiosity traps compared to those with prediction error curiosity.
Study of repeated games with unobserved agent rewards using MAB framework.
problem Designing policies for principals in repeated principal-agent games with unobservable agent rewards.
method Developed a policy achieving low regret (square-root regret up to a log factor) for perfect-knowledge agents.
result Constructed an estimator for agent's expected reward and designed a policy achieving low regret.
New method makes reinforcement learning robust to heavy-tailed rewards.
problem Heavy-tailed rewards cause statistical outliers in reinforcement learning.
method Dynamic gradient clipping in TD learning and NAC.
result Provably robust TD and NAC achieve optimal sample complexities.
Optimizes reinforcement learning controllers for reliability.
problem Lack of robustness in reinforcement learning controllers due to deterministic reward.
method Introduces a reliability-based optimization framework using a model-based approach.
result Stable controllers learned in static and dynamic environments on classical tasks.
Berry et al. (1997) initiated the development of the infinite arms bandit problem. They derived a regret lower bound of all allocation strategies for Bernoulli rewards with uniform priors, and proposed strategies based on success runs. Bonald and Proutière (2013) proposed a two-target algorithm that achieves the regret…
In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such stochastic elements are often numerous and cannot be known in advance, and they have a tendency to obscure the underlying rewards and punishm…
This paper improves understanding of GAIL's generalization and computational efficiency.
problem Understanding the theoretical properties of GAIL, especially its generalization and computational aspects.
method Investigates GAIL's theoretical properties, showing guarantees for generalization and computational efficiency.
result GAIL can be efficiently solved by stochastic first order optimization algorithms with sublinear convergence.
New algorithm minimizes regret in multi-agent bandit problem with probabilistic communication.
problem Minimizing group regret in multi-agent multi-armed bandit problem with probabilistic communication.
method Proposes a new UCB-based algorithm for decentralized multi-agent multi-armed bandit problem on d d d -regular graphs with probabilistic communication. result The proposed algorithm outperforms state-of-the-art algorithms in minimizing group regret.
Paper tackles best arm identification with cost consideration.
problem Best arm identification with cost consideration in product development.
method Derives a theoretical lower bound and proposes algorithms CTAS and CO.
result Simple algorithms can deliver near-optimal performance.
New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.
problem Learning optimal policy for average reward in uniformly ergodic MDPs.
method Developed an estimator with sample complexity of O(|S||A|t_{mix}ε^{-2}).
result First algorithm to match lower bound of existing literature.
A UCB algorithm reduces regret in cooperative multi-agent graph bandits.
problem Cooperative multi-agent decision-making on a graph with shared rewards.
method Upper Confidence Bound (UCB) algorithm for minimizing regret.
result The Multi-G-UCB algorithm achieves expected regret O ( γ N log ( T ) [ K T + D K ] ) O(γN\log(T)[\sqrt{KT} + DK]) O ( γ N log ( T ) [ K T + D K ]) . A new algorithm tackles delayed combinatorial semi-bandit with causal relations.
problem Optimizing decisions in a non-stationary environment with delayed and causally related rewards.
method Formalized as a non-stationary delayed combinatorial semi-bandit problem, the approach models causal relations with a directed graph in a stationary structural equation model. The agent learns these relations from delayed feedback to optimize decisions.
result Proved a regret bound for the proposed algorithm's performance.
New strategy for gambling with changing environments achieves sub-linear regret.
problem Optimizing rewards in a non-stationary X \mathcal{X} X -armed bandit problem. method Proposes a novel strategy for environments that change behavior abruptly.
result Proves the proposed strategy attains sub-linear cumulative regret.
Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.
problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.
Study preference-based reinforcement learning in episodic kernel MDPs.
problem Learning from episodic human preferences in reinforcement learning.
method Developed preference-based value estimation and confidence sets for kernel-based MDPs.
result Proved high-probability regret bounds that converge to optimal policy value.
New algorithm for multi-player bandits without needing lower bounds or scaling inversely.
problem Multi-player bandits without collision sensing information.
method Proposes a novel algorithm that circumvents two problems of existing algorithms.
result Proves a theoretical regret upper bound and shows superior performance in practice.
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of learning control policies for unknown linear dynamical systems so as to maximize…
Develops neural network framework for risk-reward optimization problems.
problem Multi-period risk-reward optimization with constrained policies.
method Neural network framework with two coupled feedforward networks, parametrizing two-step policies.
result Empirical optimum converges to true optimal value as network capacity and training size increase.
New algorithms optimize risk-aware selection in uncertain rewards.
problem Balancing expected reward and risk in uncertain, potentially heavy-tailed rewards.
method Distribution oblivious algorithms that consider CVaR, not bound on moments/tails.
result Provable upper bounds on incorrect identification probability.
Multi-armed bandit (MAB) is a class of online learning problems where a learning agent aims to maximize its expected cumulative reward while repeatedly selecting to pull arms with unknown reward distributions. We consider a scenario where the reward distributions may change in a piecewise-stationary fashion at unknown …
Improved exploration in factored average-reward MDPs reduces regret.
problem Minimizing regret in unknown Factored Markov Decision Processes (FMDPs).
method DBN-UCRL strategy, inspired by UCRL2, uses Bernstein-type confidence sets for individual elements of the transition function.
result Achieves a regret bound with a leading term strictly improving over existing bounds.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.