Kernel-based function approximation improves reinforcement learning performance.
problem Average reward reinforcement learning in infinite horizon settings.
method Optimistic algorithm based on kernel ridge regression.
result No-regret performance guarantees and confidence intervals for kernel-based predictions.
New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.
problem Infinite-horizon average-reward reinforcement learning with linear MDPs.
method Approximate by discounted-reward MDPs and apply optimistic value iteration.
result Achieves O(sqrt(T)) regret with polynomial complexity.
New findings on universal learning in contextual bandits with adversarial rewards.
problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.
Optimizes algorithms for non-concave bandit problems.
problem Optimizing algorithms for non-concave bandit problems.
method Unified zeroth-order optimization paradigm.
result Minimax-optimal algorithms in the dimension for low-rank generalized linear bandit problems.
A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
New approach uses unlabeled prior data to accelerate exploration in sparse reward tasks.
problem Sparse reward tasks in reinforcement learning.
method Learn reward model from online experience, label prior data, and use concurrently.
result Rapid exploration in challenging sparse-reward domains.
New algorithm reduces regret for logistic bandits without κ κ κ dependency.
problem Logistic bandits have poor frequentist regret guarantees due to large κ κ κ . method Optimistic algorithm based on self-normalized martingale tail-inequality.
result Achieves i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) regret with no κ κ κ dependency. Unified algorithm for optimizing rewards in stochastic path problems.
problem Optimizing rewards in stochastic path problems with unknown reward scales.
method A simple optimistic algorithm with regret guarantees.
result Regret bound matches best known results for SSP with all non-positive rewards.
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
New algorithm reduces regret in delayed feedback generalised linear bandits.
problem Regret in delayed feedback generalised linear bandits.
method Adaptation of optimistic algorithm to delayed feedback.
result Achieves a regret bound independent of the horizon's delay penalty.
New algorithm for recommending best arms with aggregated feedback.
problem Finding the best arm under aggregated feedback when precise rewards are unavailable.
method Gaussian Process Optimistic Optimisation (GPOO) algorithm with adaptive tree construction.
result The proposed algorithm achieves new simple regret bounds with aggregated feedback.
Proposes Optimistic Pessimistically Initialised Q-Learning (OPIQ) for better exploration in RL.
problem Pessimistic initialisation of Q-values in deep RL leads to poor exploration performance.
method Augments pessimistically initialised Q-values with count-based bonuses to ensure optimism.
result OPIQ outperforms non-optimistic DQN variants in hard exploration tasks.
This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.
problem The gap between theoretical worst-case regret analysis and empirical performance in MBRL.
method Reward randomization in model-based reinforcement learning (MBRL) with kernelized linear regulator (KNR) model.
result Reward randomization guarantees partial optimism and near-optimal worst-case regret.
New RL algorithm optimizes policies with bandit feedback, matching previous bounds.
problem Optimizing policies with unknown transitions and bandit feedback.
method Optimistic Trust Region Policy Optimization (TRPO) algorithm.
result Sub-linear regret bounds for both stochastic and adversarial rewards.
New algorithm for average reward learning with bounded hitting time assumption.
problem Minimizing regret in average reward reinforcement learning with bounded hitting time.
method Optimistic Q-learning with a novel L ‾ \overline{L} L operator for bounded hitting time. result Regret bound of i l d e O ( H 5 S A T ) ilde{O}(H^5 S\sqrt{AT}) i l d e O ( H 5 S A T ) for average reward learning. Safe linear bandits over unknown polytopes avoid safety violations and suboptimal actions.
problem Online approach to linear programming with unknown constraints and risks.
method Doubly-optimistic strategy (DOSS) for safe linear bandits over polytopes.
result DOSS achieves tight bounds on efficacy regret and safety violations.
Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.
problem Maximizing reward while avoiding unsafe arms under safety risk constraints.
method Doubly optimistic strategies with pseudo-regret formulation.
result Logarithmic regret bounds for safe multi-armed bandits.
New method boosts skill learning by encouraging optimistic exploration.
problem Intrinsic reward for exploration is inherently pessimistic.
method Derive an information gain auxiliary objective involving an ensemble of discriminators and rewarding policy disagreement.
result Improves skill learning in grid worlds and Atari games.
Optimistic Thompson Sampling reduces regret in unknown multi-player games.
problem Navigating uncertainty in unknown multi-player games with strategic decision-making.
method Introduces Thompson Sampling algorithms that exploit opponents' actions and reward structures.
result Achieves over tenfold improvements in experimental budgets with logarithmic regret bound.
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.
Paper introduces DOO models to outperform SAA out-of-sample.
problem Outperforming SAA in out-of-sample performance.
method Introduces DOO models that consider both worst-case and best-case scenarios.
result DOO models can always outperform SAA out-of-sample.
Study designs steering rewards for MFGs with unknown dynamics and model uncertainty.
problem Designing incentives for large populations of agents in MFGs with uncertain model details.
method Developed optimistic exploration algorithms for agents with no-adaptive regret behaviors.
result Sub-linear regret guarantees for cumulative gaps between agent behaviors and desired outcomes.
We propose a bandit algorithm that explores by randomizing its history of rewards. Specifically, it pulls the arm with the highest mean reward in a non-parametric bootstrap sample of its history with pseudo rewards. We design the pseudo rewards such that the bootstrap mean is optimistic with a sufficiently high probabi…
New algorithms reduce contextual bandits' regret without knowing reward noise variances.
problem Reducing regret in contextual bandits with unknown reward noise variances.
method Developed new algorithms based on the optimism principle.
result Regret scales as the square root of the sum of measurement variances, not the time horizon.
Reinforcement learning with trajectory feedback instead of state-action rewards.
problem Frequent feedback not available in practice.
method Extended reinforcement learning algorithms using trajectory feedback for known and unknown transition models.
result Hybrid optimistic-Thompson Sampling algorithm for unknown transition models.
New algorithm achieves consistent learning from context in bandit problems.
problem Learning from context in bandit problems with non-i.i.d. contexts.
method Optimistically universal learning rule balancing generalization and personalization.
result Achieves universal consistency for large classes of non-i.i.d. contexts.
PROPO tackles non-stationary MDPs with efficient policy optimization.
problem Non-stationary MDPs with varying reward and transition kernels.
method PROPO, a periodic restarted optimistic policy optimization algorithm with sliding-window-based policy evaluation and improvement.
result PROPO achieves near-optimal performance in non-stationary MDPs.
An algorithm for maximizing rewards under linear cost constraints.
problem Maximizing rewards while adhering to cost constraints in a linear bandit problem.
method Proposes an upper-confidence bound algorithm called optimistic pessimistic linear bandit (OPLB) for constrained contextual linear bandits.
result Proves an O ~ ( d T τ − c 0 ) \widetilde{\mathcal{O}}(\frac{d\sqrt{T}}{τ-c_0}) O ( τ − c 0 d T ) bound on regret for the proposed algorithm. New algorithm achieves nearly optimal regret with one-pass updates for GLB problems.
problem Generalized linear bandits with non-linear reward distributions.
method Jointly efficient algorithm using OMD estimator with one-pass updates.
result Nearly optimal regret bound with O ( 1 ) \mathcal{O}(1) O ( 1 ) time and space complexities per round. New rule reduces exploration regret to logarithmic, improving bad episode handling.
problem Improving exploration regret in average reward MDPs.
method Replacing Doubling Trick with Vanishing Multiplicative rule in EVI-based algorithms.
result Regret is logarithmic under the new rule, significantly better than linear.
Optimistic Mirror Descent framework improves bidding strategies in non-stationary first-price auctions.
problem Optimizing bidding strategies in non-stationary first-price auctions.
method Introducing Optimistic Mirror Descent (OMD) framework with novel optimism configuration.
result Minimax-optimal dynamic regret rates achieved for non-stationary first-price auctions.
PROWL uses robust reward estimates to improve ITR selection.
problem Reward uncertainty in ITR estimation leads to inflated performance.
method PAC-Bayesian framework with reward uncertainty certificates.
result PROWL achieves better robust treatment regime estimation.
New RL method explores environments without rewards, achieving efficient policy generation.
problem Efficiently exploring unknown environments without predefined rewards.
method Optimistic value-iteration algorithm with kernel and neural function approximations.
result Achieves O ~ ( 1 / ε 2 ) \widetilde{\mathcal{O}}(1 /\varepsilon^2) O ( 1/ ε 2 ) sample complexity for generating policies or equilibria. Optimistic algorithm reduces regret in non-stationary linear MDPs.
problem Efficient learning in non-stationary linear MDPs with evolving reward and transition.
method OPT-WLSVI, an optimistic model-free algorithm using exponential weights.
result Achieves a regret bound of O ~ ( d 5 / 4 H 2 Δ 1 / 4 K 3 / 4 ) \widetilde{\mathcal{O}}(d^{5/4}H^2 Δ^{1/4} K^{3/4}) O ( d 5/4 H 2 Δ 1/4 K 3/4 ) . VO Q Q Q L optimizes RL with sparse rewards using weighted bounds.
problem Sparse rewards and non-linear function approximation in RL.
method VO Q Q Q L combines Q Q Q -learning with weighted bounds for optimal regret. result Achieves asymptotically optimal regret for linear function approximation.
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.
OPPO optimizes policy learning with provable efficiency.
problem Designing efficient policy optimization algorithms that incorporate exploration.
method Proposes an Optimistic Proximal Policy Optimization (OPPO) algorithm.
result Achieves i l d e O ( d 2 H 3 T ) ilde{O}(\sqrt{d^2 H^3 T} ) i l d e O ( d 2 H 3 T ) regret in episodic MDPs. Paper optimizes learning MDPs with adversarial rewards using linear models.
problem Learning MDPs with adversarial rewards and changing reward functions.
method Proposes POWERS, an optimistic policy optimization algorithm.
result Achieves nearly optimal regret bound of O ( d H T ) O(dH\sqrt{T}) O ( d H T ) . New algorithms ensure policies perform at least as good as a baseline in reinforcement learning.
problem Learning policies that are guaranteed to perform at least as well as a baseline in reinforcement learning.
method Introduce conservative exploration for average reward and finite horizon problems, presenting two optimistic algorithms.
result Guaranteed performance of policies at least as good as a baseline, without hindering learning ability.
Algorithm learns optimal coordination for strategic agents in uncertain settings.
problem Optimizing rewards for strategic agents with private types and actions.
method Combines delaying mechanism, reward angle estimation, and LinUCB algorithm.
result Near optimal regret bound of O ~ ( T ) \tilde{O}(\sqrt{T}) O ~ ( T ) for learning optimal policy. The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.
problem Balancing exploration and exploitation in CMDPs to satisfy constraints.
method Two approaches: optimistic planning and incremental updates of primal and dual variables.
result Both approaches achieve sublinear regret on utility and constraint violations, with stronger guarantees for the linear programming approach.
Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.
problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.
New algorithm for reinforcement learning in uncertain environments with unknown thresholds.
problem Safety in reinforcement learning in unknown and uncertain environments.
method Growing-Window estimator sampling and Stochastic Pessimistic-Optimistic Thresholding (SPOT) algorithm.
result Achieves sublinear regret and constraint violation of i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) . Adversarial CBO optimizes under interventions by adversaries and non-stationarities.
problem Optimizing in the presence of adversaries and non-stationary factors.
method Formalizes CBO as ACBO, introduces CBO-MW algorithm combining online learning and causal modeling.
result First algorithm with bounded regret for ACBO, achieving superior performance in synthetic and real-world environments.
Bayesian classifier improves robustness with optimistic score ratio.
problem Limited information on class-conditional distribution.
method Optimistic score ratio for robust binary classification.
result Bayesian classifier using optimistic score ratio is robust and computationally tractable.
This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly, gradient-based algorithms for approximate upper and lower bounds are introduced. Finally…
New algorithm explores reinforcement learning with noisy data.
problem Exploration in reinforcement learning with complex value functions.
method Randomized exploration with i.i.d. scalar noises and optimistic reward sampling.
result Achieves worst-case regret bound of O ~ ( p o l y ( d E H ) T ) \widetilde{O}(\mathrm{poly}(d_EH)\sqrt{T}) O ( poly ( d E H ) T ) . The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or agains…