Deep learning approximates poker probabilities efficiently.
problem Intractable calculation of poker probabilities using combinatorics.
method Deep learning to approximate probabilities from Monte Carlo simulations.
result Deep learning model provides high-accuracy probabilities efficiently.
Algorithms for equilibrium computation generally make no attempt to ensure that the computed strategies are understandable by humans. For instance the strategies for the strongest poker agents are represented as massive binary files. In many situations, we would like to compute strategies that can actually be implement…
Paper addresses theoretical risks in neural MCCFR, proposing Robust Deep MCCFR for improved performance.
problem Theoretical risks in neural MCCFR, especially in large games.
method Adaptive framework with selective component deployment, including target networks, exploration, and variance-aware training.
result Robust Deep MCCFR achieves significant exploitability improvements in both Kuhn and Leduc Poker.
ISMCTS-BR learns best responses in large games, approximating worst-case performance.
problem Learning robustness to worst-case outcomes in large games.
method ISMCTS-BR, a scalable search-based algorithm for deep reinforcement learning.
result ISMCTS-BR approximates worst-case performance in large games.
Paper tackles learning unknown game parameters from observations.
problem Learning unknown game parameters in games where parameters are not known to all agents.
method Proposes a differentiable, end-to-end learning framework for normal and extensive form games.
result Demonstrates effective learning of game parameters in poker and security game tasks.
Neural Replicator Dynamics improves deep RL performance in nonstationary environments.
problem Nonstationarity and instability in multiagent reinforcement learning.
method Derive a new algorithm using replicator dynamics to bypass softmax in policy gradient methods.
result Neural Replicator Dynamics (NeuRD) outperforms policy gradient methods in nonstationary environments.
A new algorithm LONR learns without terminal states or perfect recall.
problem Learning in settings without terminal states or perfect recall.
method Local No-Regret Learning (LONR) using Q-learning-like updates.
result LONR achieves last iterate convergence in challenging settings.
NeuPL learns diverse policies in strategy games efficiently.
problem Iterative training of policies in strategy games leads to under-trained good-responses and wasteful repetition.
method NeuPL uses a single conditional model to represent a population of policies, offering convergence guarantees and transfer learning.
result NeuPL achieves better performance and efficiency across various domains, enabling access to novel strategies.
Paper examines actor-critic methods for RL in partially observable multiagent environments.
problem Optimizing policies in partially observable multiagent settings.
method Actor-critic algorithms, focusing on policy gradient and regret minimization.
result Shows convergence guarantees and improved performance in zero-sum games.
New algorithm improves performance in nontransitive games.
problem Nontransitive games lack a clear winner.
method Geometric framework for agent objectives, PSRO_rN algorithm.
result PSRO_rN consistently outperforms alternatives in nontransitive games.
Deep RL improves Diplomacy performance, outperforming previous methods.
problem Applying RL to complex, many-agent, simultaneous-move games like Diplomacy.
method Best response policy iteration and fictitious play approximation.
result Deep RL agents convincingly outperform previous Diplomacy agents.
New theorem guarantees approximate equilibrium in non-convex games.
problem No guarantee of equilibrium in non-convex games.
method Introduced a minimax theorem for non-convex games involving neural networks.
result Provided an approximate minimax theorem for non-convex games.
Study shows resampling labels improves classifier performance in noisy data.
problem Balancing sample size vs label reliability in noisy data.
method Comparing different validation strategies and analyzing MNIST database with varying noise levels.
result Classifier performance declines with high incorrect labels, highlighting the importance of resampling.
Model predicts stock market volatility, leading to successful trading.
problem Real-time risk management in stock markets.
method Algebraic theory of news impact, Bessel and hypergeometric functions, ML procedures.
result Trading system proved successful in historical and real-time experiments.
DeepRole learns to play hidden role games like Avalon.
problem Learning cooperation in uncertain multi-agent settings.
method Combines CFR and deep learning with deductive reasoning.
result DeepRole outperforms other agents and humans in Avalon.
Paper models human motivations in games using inverse RL.
problem Lack of understanding human motivations in game models.
method Multi-Motivation Behavior Modeling (MMBM) using inverse reinforcement learning.
result Reveals significant differences in value structures among player groups.
Hanabi game challenges AI with cooperative, imperfect information.
problem Developing AI capable of understanding others' beliefs and intentions.
method Introducing the Hanabi Learning Environment and experimental framework.
result Hanabi highlights the importance of theory of mind reasoning in AI.
Abc-boost is a new line of boosting algorithms for multi-class classification, by utilizing the commonly used sum-to-zero constraint. To implement abc-boost, a base class must be identified at each boosting step. Prior studies used a very expensive procedure based on exhaustive search for determining the base class at …
Paper tackles multiplayer symmetric games, securing equal share for n players.
problem Multiplayer games lack unique equilibria, making guarantees unreliable.
method Identifies conditions for equal share, designs efficient algorithms inspired by no-regret learning.
result Proves algorithms achieve approximate equal share across various settings.
Expanding models in neural fictitious play improves reinforcement learning efficiency and robustness.
problem Forgetting old opponents after training new ones in reinforcement learning.
method Train a single model with sub-models and a selector, expanding the model with new sub-models and updating the selector to maintain a behavior strategy.
result Improves learning efficiency and robustness of neural fictitious play.
Selective privacy framework for recommender systems.
problem Adversarial nature of collaborative filtering to user privacy.
method Selective privacy preserving (SP2) framework with two-step process.
result Users can control what ratings are publicly shared, leading to more accurate recommendations.
This chapter reviews recent advances in multi-agent reinforcement learning.
problem Theoretical foundations for multi-agent reinforcement learning are lacking.
method Selective overview of MARL algorithms with theoretical analysis.
result Identification of new research directions in MARL theory.
Deep networks achieve linear separability through progressive folding of data in higher dimensions.
problem How feed-forward networks achieve linear separability for classification tasks.
method Progressive folding of the data manifold in unoccupied higher dimensions.
result The folding operation allows efficient solutions by providing access to arbitrary regions in the distribution.