New algorithm optimally identifies best arm in both stochastic and adversarial settings.
problem Best arm identification in stochastic and adversarial reward scenarios.
method Parameter-free algorithm designed to be robust to adversarial rewards and optimal in stochastic problems.
result Algorithm's error rate matches optimal bounds in stochastic problems and is robust to adversarial rewards.
Study non-linear combinatorial bandits with polynomial rewards, finding significant differences from linear cases.
problem Adversarial combinatorial bandits with general non-linear reward functions.
method Extending existing work on adversarial linear combinatorial bandits, analyzing minimax optimal regret for polynomial and non-polynomial reward functions.
result Minimax optimal regret bounds for adversarial combinatorial bandits with general non-linear reward functions.
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.
New reward function improves GAIL performance in task-based environments.
problem Reward bias in adversarial imitation learning.
method Proposed a new reward function to overcome existing biases.
result New reward function outperforms existing methods in task-based environments.
A multi-player bandit system resists adversarial attacks with near-optimal regret.
problem Adversaries attempt to manipulate rewards in a multi-player multi-armed bandit game.
method Players communicate a single bit to resist attacks, achieving near-optimal regret.
result Achieves near-optimal regret of O ( log 1 + δ T + W ) O(\log^{1+δ}T + W) O ( log 1 + δ T + W ) , where W W W is the total time of adversarial attacks. Improves imitation learning in RL by learning reward function efficiently.
problem Lack of effective reward function approximation in AIRL for imitation tasks.
method Proposes Off-Policy AIRL that combines adversarial learning with efficient reward function approximation.
result Shows superior imitation performance and efficiency compared to state-of-the-art AIL algorithms.
AIRL learns robust, generalizable reward functions from demonstrations.
problem Learning robust reward functions from demonstrations for changing environments.
method Adversarial Inverse Reinforcement Learning (AIRL) with hierarchical disentangled rewards.
result Generalizable policies and comparable results to state-of-the-art methods.
The paper shows how policy regularization acts like an adversary to improve robustness.
problem Improving robustness of learned policies in reinforcement learning.
method Using convex duality, the paper characterizes adversarial reward perturbations and provides generalization guarantees.
result Policy regularization acts as an adversary to improve robustness against worst-case reward perturbations.
SAIL improves AIL by weighting adversarial rewards with support estimation.
problem Training instability and reward bias in AIL.
method Support-weighted Adversarial Imitation Learning (SAIL) extends AIL with support estimation to improve reinforcement signals.
result SAIL achieves better performance and stability on benchmark tasks.
WDAIL uses Wasserstein distance for more effective reward shaping in IL.
problem Fixed reward functions in GAIL limit performance on complex tasks.
method Introduces Wasserstein distance and PPO for improved reward shaping and stability.
result Significant performance improvement in complex MuJoCo tasks.
Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.
problem Multi-armed bandit with composite and anonymous feedback, especially without reward interval size knowledge.
method Proposed adaptive algorithms for stochastic and adversarial cases, without reward interval knowledge.
result First algorithm for adversarial case handling non-oblivious adversary and unknown reward interval size.
TRAIL improves robot imitation learning by focusing on task-relevant features.
problem Discriminator networks learn spurious associations, providing poor reward signals.
method Constrained discriminator optimization to learn task-relevant rewards.
result TRAIL outperforms GAIL and behaviour cloning in robotic manipulation tasks.
Adversarial RL recovers agent rewards from financial market data simulations.
problem Recovering agent rewards in volatile financial markets with unknown dynamics.
method Adversarial inverse reinforcement learning in latent space simulations.
result Adversarial RL can robustly recover agent rewards from latent space representations of real market data.
This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproduc…
Regularized policies are robust to adversarial rewards.
problem Understanding the effects of regularization on policy exploration and robustness.
method Using Fenchel duality to derive the dual problem of the regularized RL objective, showing the optimal policy is robust to adversarial rewards.
result Regularized policies are optimal for a reinforcement learning problem under adversarial reward conditions.
Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.
problem Maximizing total reward in multi-agent bandits with adversarial corruptions.
method Proposes a cooperative learning algorithm robust to adversarial corruptions.
result Demonstrates an additive O ( ( L / L min ) C ) O((L / L_{\min}) C) O (( L / L m i n ) C ) regret term for an adversary with unknown corruption budget. Attackers can significantly reduce team rewards in cooperative multi-agent reinforcement learning.
problem Robustness of cooperative multi-agent reinforcement learning to adversaries.
method Novel attack method involving training a policy network and using targeted adversarial examples.
result Reduces team reward from 20 to 9.4 by attacking a single agent, reducing winning rate from 98.9% to 0%.
Study on reward poisoning attacks on CMAB, revealing attackability depends on adversary's knowledge.
problem Reward poisoning attacks on Combinatorial Multi-Armed Bandits (CMAB).
method Provided a sufficient and necessary condition for attackability, devised an attack algorithm.
result Attackability of CMAB depends on adversary's knowledge of the bandit instance.
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowe…
AMIGo uses adversarial intrinsic goals to teach RL agents new skills.
problem Learning in sparse reward environments.
method Adversarial intrinsic goals to generate a curriculum for a student policy.
result AMIGo enables agents to learn new skills without extrinsic rewards.
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.
Paper addresses reward learning issues in RL, improving both under- and over-estimation.
problem Reward learning from data can lead to reward delusions or underestimation, causing unintended behaviors.
method Connects reward learning to positive-unlabeled (PU) learning and applies a large-scale PU learning algorithm.
result Improves both GAIL and supervised reward learning without additional assumptions.
Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
problem Inadequate policy imitation and limited transferable reward recovery in AIRL.
method Substituted built-in algorithm with SAC for policy updating and proposed PPO-AIRL + SAC hybrid framework.
result SAC improves policy imitation but hinders reward recovery; PPO-AIRL + SAC achieves satisfactory transfer effect.
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.
New models for bandit problems with fidelity rewards are introduced and analyzed.
problem Fidelity rewards in bandit problems to incentivize loyalty.
method Two models (loyalty-points and subscription) for fidelity rewards; stochastic and adversarial settings considered.
result Sublinear regret bounds for some models, worst case lower bounds for others.
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 ) . DSAC improves robustness of imitation learning.
problem Learning from few expert data and distribution shift.
method DSAC uses adversarial reward function.
result DSAC performs well on PyBullet environments.
New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.
problem Learning in episodic RMAB with unknown transition functions and adversarial rewards.
method Developed a novel RL algorithm with a biased reward estimator and an index policy.
result Achieved i l d e O ( H T ) ilde{\mathcal{O}}(H\sqrt{T}) i l d e O ( H T ) regret bound for adversarial RMAB. This paper studies GAIL's global convergence for general MDP and nonlinear rewards.
problem Understanding when GAIL algorithms achieve global convergence for general MDP and nonlinear rewards.
method Characterization of global convergence for various policy gradient algorithms applied to GAIL.
result First systematic theoretical study of GAIL for global convergence.
This paper optimizes attacks on stochastic bandits and proposes defenses against them.
problem Optimizing adversarial attacks on stochastic bandit algorithms.
method Designs optimal attack strategies and proposes defense algorithms.
result Optimal attack strategies and defense algorithms achieve near perfect performance.
Contextual bandits study how reward variance affects regret bounds.
problem Investigating how small reward variance impacts regret bounds in contextual bandits.
method Analyzing two types of adversaries and function approximation complexities.
result Regret bounds are influenced by the eluder dimension and reward variance.
Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, …
Imitation Learning describes the problem of recovering an expert policy from demonstrations. While inverse reinforcement learning approaches are known to be very sample-efficient in terms of expert demonstrations, they usually require problem-dependent reward functions or a (task-)specific reward-function regularizatio…
New framework for efficient query-based imitation learning.
problem Aligning agent policy with human expert behavior without prior knowledge.
method Adversarial reward query with successor representation.
result Significantly outperforms uncertainty-based methods in query efficiency.
New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework to automatically acquire suitable reward functions…
INF-clip optimizes heavy-tailed MAB problems with improved performance.
problem Optimizing multi-armed bandit problems with heavy-tailed rewards.
method INF-clip algorithm for adversarial and stochastic heavy-tailed MAB settings.
result INF-clip is optimal for linear and non-linear heavy-tailed stochastic MAB problems.
The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conventional approach of hard-coding motion routines, we propose a deep learning method for obtaining control policies by directly mimicking raw…
This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget B B B that can be spent to perform actions, an…
New algorithm resists corruption in linear contextual bandits.
problem Adversarial corruption in linear contextual bandits.
method Variance-aware algorithm with multi-level partition and adaptive confidence sets.
result Regret bound of i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) ilde{O}(C^2d\sqrt{\sum_{t = 1}^T σ_t^2} + C^2R\sqrt{dT}) i l d e O ( C 2 d ∑ t = 1 T σ t 2 + C 2 R d T ) . I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, includi…
Multi-armed bandits a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, textbook-like treatment of the subject. Each chapter tackles a p…
New algorithm robust to probabilistic unbounded adversarial attacks in bandit problems.
problem Powerful adversaries that can catastrophically perturb the revealed reward in bandit problems.
method Proposes med-E-UCB and med- ε ε ε -greedy algorithms based on sample median for robustness. result Achieves O ( log T ) \mathcal{O}(\log T) O ( log T ) pseudo-regret under arbitrary and unbounded reward perturbation. 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.
This paper studies poisoning attacks in episodic RL and discovers their effectiveness depends on reward bounds.
problem Understanding security threats to RL algorithms through poisoning attacks.
method Examined two types of poisoning attacks: reward and action manipulation, in bounded and unbounded reward settings.
result The effectiveness of poisoning attacks depends on reward bounds, with different attack costs and success rates.
New UCB algorithms resist contamination in bandit problems.
problem Stochastic bandit problems with ε-contaminated rewards.
method Robust mean estimators and crUCB algorithms.
result Achieves O(√KTlogT) regret for small contamination proportions.
There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly defined, making the application of RL challenging. In this paper, we propose a …
Robust Q-learning algorithm resists corrupted rewards.
problem Non-ideal environments with corrupted rewards.
method Developed a novel robust Q-learning algorithm using historical data.
result Finite-time convergence rate matches state-of-the-art bounds.