Deep RL fails on deceptive games, revealing algorithm weaknesses.
problem Characterizing and understanding failures of deep reinforcement learning.
method Testing A2C on four deceptive games using a game framework.
result Deep RL fails in specific ways that differ from planning-based agents.
This paper tackles hard exploration in the game Pommerman, improving RL learning.
problem Hard exploration in sparse, delayed, and deceptive reward domains.
method Developed a model-based automatic reasoning module to prune unsafe actions.
result Model-based approach significantly improves RL learning in Pommerman.
New approach simulates reputation dynamics using information compression.
problem Malicious communication strategies in reputation networks.
method Uses information compression techniques to simulate social phenomena.
result Emergent phenomena like echo chambers and deception are observed.
Study investigates how AI can create and detect deceptive explanations, finding they can fool humans but ML can detect them.
problem The risk of deceptive AI explanations increasing trust issues and economic risks.
method Investigates creation and detection of deceptive explanations using AI models and machine learning methods.
result Deceptive explanations can fool humans, but ML can detect them with high accuracy.
Unified pipeline detects multi-turn deception using geometric signals.
problem Detecting multi-turn deceptive interactions in LLMs.
method Geometric signaturization via genetic prompt optimization.
result Compact geometric model achieves high recall and F1 scores.
Q*BERT learns to navigate text-based games by building a knowledge graph.
problem Text-based games have bottlenecks that standard RL agents struggle to overcome.
method Q*BERT learns a knowledge graph and uses intrinsic motivation to detect and overcome bottlenecks.
result Q*BERT outperforms state-of-the-art agents in text games, including Zork.
FATE framework attacks graph learning models to amplify bias deceptively.
problem Achieving poisoning attacks on graph learning models to exacerbate bias deceptively.
method Bi-level optimization problem and meta learning-based framework named FATE.
result FATE amplifies bias of graph neural networks while maintaining downstream task utility.
The study detects deceptive language in business communication using AI.
problem Deceptive language in business communication.
method Combining classical rhetoric, communication psychology, and linguistic theory with computational textual analysis and transformer models.
result Detection accuracies of over 99% achieved in controlled settings.
This paper explores how diverse neural network ensembles improve prediction accuracy and robustness against deception.
problem Improving prediction accuracy and robustness of neural networks against adversarial attacks.
method Examines and measures ensemble diversity, develops algorithms for creating and combining diverse ensembles.
result Greater diversity in neural network ensembles leads to higher accuracy and robustness against deception.
Framework trains safe agents avoiding deceptive behavior.
problem Training safe agents from unsafe incentives.
method Formal settings, causal influence analysis, maximizing non-mediated effects.
result Agents avoid manipulating delicate state for rewards.
Systematic review of ML models for detecting social media deception.
problem Detecting fake news, spam, and fake accounts on social media.
method 36 studies evaluated using PROBAST tool, identifying biases and limitations.
result Over-reliance on accuracy in imbalanced data settings is a flaw.
XEnsemble improves DNN robustness against adversarial and out-of-distribution inputs.
problem Protecting DNN models from adversarial and out-of-distribution inputs.
method Diverse input denoising verifiers and disagreement-diversity ensemble learning.
result XEnsemble achieves high defense and detection success rates.
Improved sample efficiency in reinforcement learning with action guidance.
problem Sample inefficiency in deep reinforcement learning with sparse, delayed, and deceptive rewards.
method Integrating a non-expert demonstrator (e.g., MCTS) into asynchronous distributed deep reinforcement learning.
result Our methods learn faster and converge to better policies on a game.
RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.
problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.
In online discussion communities, users can interact and share information and opinions on a wide variety of topics. However, some users may create multiple identities, or sockpuppets, and engage in undesired behavior by deceiving others or manipulating discussions. In this work, we study sockpuppetry across nine discu…
This paper optimizes cybersecurity resource allocation in networks with heterogeneous attacker and defender valuations.
problem Optimizing cybersecurity resource allocation in networks with heterogeneous attacker and defender valuations.
method Combining strategic behavior of players with contagion dynamics, a method is extended to determine optimal resource allocation based on simple network metrics weighted by risk profiles.
result The asymmetry between attacker and defender valuations drives optimal attack and defense strategies, shaping system resilience.
A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, whic…
Deep learning uses alphabet frequencies to accurately classify fake news.
problem Classifying fake news from trustworthy news.
method Used deep learning algorithms on alphabet frequencies of text without sequence information.
result Achieved high accuracy (85%) in classifying fake news.
This paper introduces a new method to deceive causal structure learning by omitting data.
problem Deceiving causal structure learning algorithms with incompletely observed data.
method Adversarial missingness attack to bias the learned causal structures.
result Theoretical and practical attack mechanisms are developed for various SCMs.
This work challenges the assumption that shorter conformal prediction intervals are always better.
problem The conventional evaluation of conformal prediction metrics (coverage and interval length) may not fully capture the quality of predictions.
method The Prejudicial Trick (PT) is introduced, which probabilistically returns either a null interval or a longer one to maintain valid coverage while potentially reducing interval length.
result The Prejudicial Trick can yield deceptively shorter intervals without compromising coverage, but introduces practical vulnerabilities.
This paper tackles sandbagging in AI safety evaluations.
problem AI agents may hide dangerous capabilities to avoid being deactivated.
method Developed a simple model of strategic deception in sequential decision-making tasks.
result Demonstrated that optimal rational agents exhibit sandbagging behavior.
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full auto…
The Economist recently reported that infrastructure spending is the largest it is ever been as a share of world GDP. With $22 trillion in projected investments over the next ten years in emerging economies alone, the magazine calls it the "biggest investment boom in history." The efficiency of infrastructure planning a…
The cost-benefit analysis formulates the holy trinity of objectives of project management - cost, schedule, and benefits. As our previous research has shown, ICT projects deviate from their initial cost estimate by more than 10% in 8 out of 10 cases. Academic research has argued that Optimism Bias and Black Swan Blindn…
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-of-the-art machine learning techniques, such as deep neural networks, can provi…
Paper presents content-based models for game recommendation in cold start scenarios.
problem Cold start problem in game recommendation where new games and players have no historical data.
method Uses survey data to develop content-based interaction models that generalize to new games, players, and both.
result Content models outperform collaborative filtering in predicting new interactions.
In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to answer this research question by creating visual analogies between a pair of game…
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a diversity-driven approach for exploration, which can be easily combined with both off- and o…
Potential games, originally introduced in the early 1990's by Lloyd Shapley, the 2012 Nobel Laureate in Economics, and his colleague Dov Monderer, are a very important class of models in game theory. They have special properties such as the existence of Nash equilibria in pure strategies. This note introduces graphical…
A new framework for playing and learning board games.
problem Tackling the tedious and repetitive aspects of coding for board game AI.
method Developed a generic TD(λ)-n-tuple agent for arbitrary board games. result TD(λ)-n-tuple outperforms other generic agents on various games. IGGP learns game rules from varying quality game play, finding no overall trend.
problem Learn game rules from varying quality game play.
method Used Sancho's intelligent game traces and ILP systems (Metagol, Aleph, ILASP) to induce game rules from traces of varying quality and volume.
result No overall trend in accuracy of learned game rules from varying quality and volume of training data.
A game on diagrams switches crossing directions to achieve connectedness.
problem Achieving connectedness in diagrams through crossing switches.
method Players switch crossing directions on regions of a diagram to achieve connectedness.
result Connectedness can be achieved through strategic crossing switches.
Introduces SM-games to analyze machine learning interactions.
problem Lack of understanding and control in n-player games.
method Introduces SM-games with pairwise zero-sum interactions.
result SM-games are amenable to first-order optimization methods.
Just as war is sometimes fallaciously represented as a zero sum game -- when in fact war is a negative sum game - stock market trading, a positive sum game over time, is often erroneously represented as a zero sum game. This is called the "zero sum fallacy" -- the erroneous belief that one trader in a stock market exch…
The existence of stationary Markov perfect equilibria in stochastic games is shown under a general condition called "(decomposable) coarser transition kernels". This result covers various earlier existence results on correlated equilibria, noisy stochastic games, stochastic games with finite actions and state-independe…
Game theory helps analyze ESOs/EBIs in production and service sectors.
problem Economic incentives affect traditional production/service functions and create intangible capital.
method Uses game theory to analyze interactions in ESO/EBI transactions.
result No perfect Nash Equilibria for two-stage games involving many participants.
Combinatorial two-player games have recently been applied to knot theory. Examples of this include the Knotting-Unknotting Game and the Region Unknotting Game, both of which are played on knot shadows. These are turn-based games played by two players, where each player has a separate goal to achieve in order to win the…
We start briefly surveying research on optimal stopping games since their introduction by E.B.Dynkin more than 40 years ago. Recent renewed interest to dynkin's games is due, in particular, to the study of Israeli (game) options introduced in 2000. We discuss the work on these options and related derivative securities …
The paper explores how regularization can lead to convergence in imperfect information games.
problem Finding equilibrium in imperfect information games with imperfect information.
method Investigates Follow the Regularized Leader dynamics and how adding a regularization term can lead to strong convergence guarantees.
result The approach leads to algorithms that converge exactly to the Nash equilibrium in imperfect information games.
Educational game on crypto investment helps students grasp macroeconomics.
problem Weak connections between microeconomic decision-making and macroeconomic concepts in classroom games.
method Design and study of an educational game on cryptocurrency investment.
result Engages students in understanding macroeconomics through incentivized individual investment decisions.
Simplified NFT games discussed with methods for extracting value.
problem Issues influencing NFT games' structure and stability.
method Three methods for extracting value from NFT games.
result Various design constraints and mutual beneficial games.
The paper proposes a method to learn continuous-action graphical games from perturbed equilibria.
problem Learning the exact structure of continuous-action graphical games from limited data.
method A ℓ12− block regularized method to recover the graphical game structure. result The method recovers the exact structure of the graphical game under certain conditions.
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose …
Paper tackles hidden game problem in AI alignment and language games.
problem Hidden game problem in AI alignment and language games.
method Developed a composition of regret minimization techniques to discover and exploit hidden structures.
result Achieved optimal external and swap regret bounds for rapid convergence to correlated equilibria.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
Gradient Descent Ascent converges to von-Neumann solution in hidden zero-sum games.
problem Understanding dynamics of zero-sum games with hidden structure.
method Gradient Descent Ascent applied to hidden zero-sum games with specific convex-concave structure.
result Gradient Descent Ascent converges to von-Neumann solution in strictly convex-concave hidden games.
Generalizes region select game to k-colored knot diagrams.
problem Play game on knot diagrams with multiple colors.
method Generalize region select game to k-colored knot diagrams. result Generalization of the region select game to k-colored knot diagrams. We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.
problem Learning equilibrium in leader-follower games with noisy bandit feedback.
method Proposed Correlated Stackelberg Equilibrium (CSE) and online learning algorithms balancing exploration and exploitation.
result Achieves no-external Stackelberg-regret, converging to approximate CSE.