betaFeedback

WorksComputer Science

Optimistic Hedge in General-Sum Games: Fundamental Limits and Regret Bounds via Temporal Approximation

Abstract

Optimistic Hedge, a multiplicative weight update with one step of extrapolation, is one of the most natural regret-minimizing dynamics for games, and characterizing its regret has been a longstanding open question. Daskalakis, Fishelson and Golowich proved that if all mm players in a finite general-sum game follow Optimistic Hedge with a fixed learning rate, each player's regret is polylogarithmic in the horizon TT. Subsequently, Ha showed that an appropriate choice of learning rate makes each player's regret bounded independently of TT. This bound, however, is non-constructive and its dependence on the number of actions nn is not explicit, leaving open whether Optimistic Hedge can achieve a constant regret bound which is polynomial in the size of the game. We show that the answer hinges on the number of players. In two-player games, there is a learning rate for which Optimistic Hedge guarantees O(nlog⁡n)O(n\log n) regret independent of the horizon. In three-player games, however, no such bound is possible: for any learning rate up to an absolute constant and for sufficiently large horizon TT, there is a game with nn actions per player in which some player's regret is 2Ω(n)2^{Ω(n)}, and more generally, for every m≥3m\ge3 we construct mm-player games in which some player's regret is 2Ω(mn)2^{Ω(mn)}; for learning rates above 2−Ω(mn)2^{-Ω(mn)}, that player's regret even grows linearly in TT. Our upper bound is based on a temporal approximation framework for the analysis of Optimistic Hedge. Starting from the variance-based RVU bound of Daskalakis et al., we approximate the losses over time-localized windows by well-behaved functions, whose total variation is a small fraction of their cumulative variance. In mm-player games, the same framework gives a significantly simplified proof of the recent O(mlog⁡nlog⁡T)O(\sqrt{m}\log n\log T) regret bound due to Ha.

Introduction

No-regret learning is a central paradigm for decision making under uncertainty and for learning in games. In each of TT rounds, a learner chooses a probability distribution xtx^t over nn actions, observes a loss vector ℓt∈[0,1]n\ell^t \in[0,1]^n, and suffers the expected loss ⟨xt,ℓt⟩\langle x^t,\ell^t\rangle. The learner’s regret, Reg⁡(T)=∑t=1T⟨xt,ℓt⟩−min⁡a∈[n]∑t=1Tℓt(a)\operatorname{Reg}(T) = \sum_{t=1}^{T}\langle x^t,\ell^t\rangle- \min_{a\in[n]}\sum_{t=1}^{T}\ell^t(a), compares their cumulative loss with that of the best fixed action in hindsight. The canonical no-regret algorithm is multiplicative weights, or Hedge [25, 17], which plays xt(a)∝exp⁡(−η∑s<tℓs(a))x^t(a) \propto\exp(-\eta\sum_{s<t}\ell^s(a)) and, for a learning rate η≃log⁡n/T\eta\simeq\sqrt{\log n/T}, guarantees Reg⁡(T)=O(Tlog⁡n)\operatorname{Reg}(T) = O(\sqrt{T\log n}) against every sequence of losses. Algorithms of this kind underlie boosting [17], fast approximate solvers for zero-sum games, linear programs and combinatorial problems [18, 3], and counterfactual regret minimization, the engine behind superhuman poker programs [44, 7]; they also model bidder behavior in ad auctions [31]. In games, when every player has regret o(T)o(T), the empirical distribution of play converges to the set of coarse correlated equilibria [22, 30], at a rate governed by the largest average regret among the players; under the stronger requirement of vanishing internal regret, it converges to correlated equilibria [19, 23].

Against an adversary, who may choose every loss vector with full knowledge of the learner’s algorithm, the rate Tlog⁡n\sqrt{T\log n} cannot be improved [8]. A player in a game, however, faces other learners rather than an adversary. If they adapt gradually, the loss vector ℓt+1\ell^{t+1} resembles ℓt\ell^t, and anticipating this may yield regret far below the adversarial rate. Optimistic Hedge [35, 36, 37] builds this anticipation into Hedge by counting the most recent loss vector twice, the second time as a prediction of the next one. Suitably tuned, it retains the adversarial guarantee of Hedge and requires no knowledge of the game and no coordination beyond a shared learning rate.

A long line of work has studied the regret of Optimistic Hedge when all mm players of a general-sum game, each with nn actions, run it with a common, fixed learning rate. Its starting point is the RVU (regret bounded by variation in utilities) property of Syrgkanis, Agarwal, Luo and Schapire [37], which bounds the regret by log⁡n/η\log n/\eta, plus a term proportional to the variation of the losses, minus one proportional to the movement of the player’s own strategy. Since strategies move by O(η)O(\eta) per round, this can be shown to yield regret O(T1/4)O(T^{1/4}). The exponent was lowered to 1/61/6 for two players by Chen and Peng [10], and the first polylogarithmic bound, O(mlog⁡nlog⁡4T)O(m\log n\log^4 T), was obtained by Daskalakis, Fishelson and Golowich [13]. Ha [21] recently improved it to O(mlog⁡nlog⁡T)O(\sqrt{m}\log n\log T), and later showed that, for a suitable learning rate, the regret is bounded by a constant C(m,n)C(m,n) independent of TT [20].

This development settles the dependence of the regret on the horizon, but not on the size of the game. The proof of [20] is non-constructive: it derives an exact finite-order linear relation among the temporal differences of the trajectory from a Noetherianity theorem of Frisch [16]. This shows that C(m,n)C(m,n) is finite, but gives no control over its dependence on mm and nn. Were C(m,n)C(m,n) exponential in nn, the constant bound would be weaker than the logarithmic one at every horizon of practical interest. Meanwhile, more elaborate dynamics, based on higher-order or multiplicative forms of optimism, were recently shown to attain horizon-independent regret polynomial in mm and nn, and even polylogarithmic in nn for external regret [24, 4, 39, 26]. As Optimistic Hedge remains the most natural and best studied of the optimistic dynamics, we ask whether its simple one-step optimism already suffices:

Does fixed-learning-rate Optimistic Hedge guarantee every player regret poly⁡(m,n)\operatorname{poly}(m,n), independently of the horizon?

We show that, perhaps surprisingly, the answer is affirmative for two players and negative for three or more, although the polylogarithmic bounds above depend on mm only polynomially.

Main results

Throughout, all players run Optimistic Hedge with a common, fixed learning rate η\eta, starting from the uniform distribution and observing their expected loss vectors. We obtain three results.

(i) Logarithmic regret for mm players. We develop a temporal approximation framework for the analysis of Optimistic Hedge, and use it to reprove the logarithmic bound of Ha [21], with the same dependence on mm and nn and with explicit constants: in every mm-player game, the learning rate η=c/(mlog⁡T)\eta= c/(\sqrt{m}\log T), for a small enough absolute constant c>0c > 0, guarantees each player regret O(mlog⁡nlog⁡T)O(\sqrt{m}\log n\log T) (Theorem 3.3).

(ii) Constant regret for two players. There is an absolute constant c>0c > 0 such that in every two-player game, any learning rate 0<η≤c/n0 < \eta\le c/n guarantees each player regret at most log⁡n/η+η\log n/\eta+ \eta at every horizon TT. In particular, η=c/n\eta= c/n gives regret O(nlog⁡n)O(n\log n) for all TT (Theorem 3.4).

(iii) An exponential barrier for three players. There are absolute constants C,η0>0C,\eta_0 > 0 such that for every n≥Cn \ge C and every learning rate 0<η≤η00 < \eta\le\eta_0, some three-player game with nn actions per player forces regret 2Ω(n)2^{\Omega(n)} on some player for all sufficiently large TT. If moreover η≥Cn2−n/8\eta\ge Cn^{2^{-n/8}}, the game can be chosen so that this player’s regret grows linearly in TT (Theorem 3.6). More generally, for m≥3m \ge3 players the lower bound becomes 2Ω(mn)2^{\Omega(mn)} (Theorem 6.24).

Our proof of (i) is short and significantly simplifies earlier polylogarithmic analyses of Optimistic Hedge [13, 21]. The bound in (ii) is explicit and polynomial in nn, and the learning rate η=c/n\eta= c/n is oblivious to both the game and the horizon. It is also tight up to an additive constant, since even against constant losses the regret of Optimistic Hedge can reach log⁡n/η−1\log n/\eta- 1. The same elementary fact gives the first part of (iii) when η<Cn2−n/8\eta< Cn^{2^{-n/8}}, so the substance of (iii) lies in its second part. Already for η=c/n\eta= c/n, some three-player game forces linear regret once nn is large, so adding a single player turns a constant regret bound into a linear one. To our knowledge, (iii) is the first lower bound for Optimistic Hedge beyond two-player zero-sum games, and it separates the algorithm from the more elaborate dynamics mentioned above.

Techniques. Through the variance form of the RVU bound [37, 13], both upper bounds reduce to bounding the variation of a player’s losses by their variance: along the trajectory of play, the variation ∑tVar⁡xt(ℓt−ℓt−1)\sum_t \operatorname{Var}_{x_t}(\ell^t-\ell^{t-1}) must be at most half the cumulative variance ∑tVar⁡xt(ℓt−1)\sum_t \operatorname{Var}_{x_t}(\ell^{t-1}), up to an additive term. Where previous work relied on the high-order smoothness of the trajectory [13, 21], we approximate the losses on short windows of time by simple functions for which such an inequality is classical. Inequalities of Markov and Bernstein type bound the derivative of a polynomial or of an exponential sum by the size of the function itself; in the integral form relevant here, every ff in the approximating class F\mathcal{F} satisfies

∫If′(s)2 ds≤CFW2∫0Wf(s)2 ds,\int_I f'(s)^2\,ds \le\frac{C_{\mathcal{F}}}{W^2}\int_0^W f(s)^2\,ds,

where II is the middle part of the interval [0,W][0,W]. We use a discrete analogue of this inequality on windows of WW rounds. For mm players, F\mathcal{F} consists of polynomials of degree O(log⁡T)O(\log T), with CF=O(log⁡2T)C_{\mathcal{F}} = O(\log^2 T), and the approximation error is paid for by the horizon. For two players, freezing the losses of player 2 on a window turns those of player 1 into ratios of sums of nn exponentials, for which a Bernstein inequality of Borwein and Erdélyi [5] gives CF=O(n2)C_F = O(n^2). Crucially, the error of freezing is paid for by the variance itself, through a feedback loop: the losses of player 2 move only when player 1 moves, and player 1 moves only when their own losses vary. A third player breaks this loop, and (iii) shows that the breakdown is not an artifact of the analysis.

The lower bound rests on the observation that optimism can also hurt. To leading order, a small periodic perturbation of frequency ω\omega in a player’s losses changes the slope of their regret in proportion to 12−cos⁡ω\frac{1}{2} - \cos\omega. Slow oscillations are anticipated by the optimistic prediction and reduce the regret, whereas fast ones throw the prediction out of phase and make the regret grow linearly. In our game, a third player observes two players driven into a cycle of period four. Since a small learning rate only produces slow oscillations, this cycle is generated by a cascade of blocks of eight actions, each driven quadratically by its predecessor and hence oscillating twice as fast; the log⁡(1/η)\log(1/\eta) blocks this requires account for the exponential barrier.

Related work

Optimism. The optimistic step goes back to Popov’s modification of the saddle-point method of Arrow and Hurwicz [32], now viewed as a single-call variant of the extragradient method and as an explicit approximation of the proximal point method [27, 34, 28]. Rakhlin and Sridharan [35, 36] brought it to online learning, building on gradual-variation bounds [11]; with the entropic regularizer, it yields Optimistic Hedge.

Optimistic Hedge in games. The analysis of [13] shows that the finite differences of the dynamics of every order kk up to O(log⁡T)O(\log T) are of order (mη)k(m\eta)^k, up to kk-dependent factors, and converts them into control of the first-order differences through a Fourier-analytic interpolation inequality. The same scheme underlies the bound of [21] and has been extended to swap regret, and hence to correlated equilibria [1]. More is known in two-player zero-sum games, where near-optimal no-regret dynamics were first designed [12]: the sum of the two regrets is bounded by a constant [36], and Optimistic Hedge’s individual regret is logarithmic in the numbers of actions, with algorithm-specific lower bounds tight for the sum of the regrets [42].

Other dynamics. Logarithmic regret is also achieved by optimistic follow-the-regularized-leader with logarithmic regularizers [2, 15] and by cautious optimism, which adapts the learning rate [40], while clairvoyant multiplicative weights approach coarse correlated equilibria at rate O(log⁡T/T)O(\log T/T) [33]. The horizon-independent bounds discussed above rely on higher-order predictors built from exponential moving averages [24] or on a discounted (m+1)(m+1)-th order extrapolation over a lifted strategy space [4], on multiplicatively optimistic regret matching [39], and, for swap regret, on two-scale higher-order optimism [26].

Cycles. Multiplicative weights and related dynamics are known to cycle, or even diverge, in zero-sum games [29, 6], where optimistic methods instead converge in the last iterate when the equilibrium is unique [14, 43], though not necessarily fast [9]. Our construction shows that in general-sum games Optimistic Hedge itself may cycle, at a high cost in regret.

Problem setting

Games. A finite (general sum) game with m≥2m \ge2 players is specified by action sets [ni]={1,…,ni}[n_i] = \{1,\ldots,n_i\} and loss functions Li:∏j=1m[nj]→[0,1]L_i : \prod_{j=1}^{m}[n_j] \to[0,1], one for each player i∈[m]i \in[m]. A mixed strategy of player ii is a probability vector xi∈Δnix_i \in\Delta_{n_i}, and a profile x=(x1,…,xm)x = (x_1,\ldots,x_m) of mixed strategies induces for each player the vector of expected losses of their actions,

ℓi(x)(ai)=∑a−iLi(ai,a−i)∏j≠ixj(aj),ai∈[ni],(1)\ell_i(x)(a_i) = \sum_{a_{-i}} L_i(a_i,a_{-i}) \prod_{j\ne i} x_j(a_j), \qquad a_i \in[n_i], \tag*{(1)}

which is multilinear in the opponents’ strategies. We write G(m,n)G(m,n) for the class of games with mm players and nn actions per player.

Repeated play and feedback. We consider a general sum game played repeatedly for TT rounds. In round tt the players simultaneously choose a mixed strategy profile xt=(x1t,…,xmt)x^t = (x_1^t,\ldots,x_m^t), and player ii observes their entire expected loss vector ℓit=ℓi(xt)∈[0,1]ni\ell_i^t = \ell_i(x^t) \in[0,1]^{n_i}. This is the full-information, expected-loss feedback model of [37, 13]; the players observe exact expectations rather than the losses of sampled action profiles. The individual (external) regret of player ii after TT rounds is

Reg⁡i(T)=∑t=1T⟨xit,ℓit⟩−min⁡a∈[ni]∑t=1Tℓit(a).(2)\operatorname{Reg}_i(T) = \sum_{t=1}^{T} \langle x_i^t,\ell_i^t\rangle- \min_{a\in[n_i]} \sum_{t=1}^{T} \ell_i^t(a). \tag*{(2)}

Optimistic Hedge. All players update their strategies using Optimistic Hedge with a common, fixed learning rate η>0\eta> 0. Each player ii starts from the uniform distribution and, having observed ℓit\ell_i^t, updates

References

  1. [1]Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, and Tuomas Sandholm. Near-optimal no-regret learning for correlated equilibria in multi-player general-sum games. In Proceedings of the ACM Symposium on Theory of Computing (STOC), 2022.DOI
  2. [2]Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, and Tuomas Sandholm. Uncoupled learning dynamics with O(log T) swap regret in multiplayer games. In Advances in Neural Information Processing Systems (NeurIPS), 2022.arxiv.org/abs/2204.11417
  3. [3]Sanjeev Arora, Elad Hazan, and Satyen Kale. The multiplicative weights update method: a meta-algorithm and applications. Theory of Computing, 8(6):121–164, 2012.
  4. [4]Omar Abbadi, Rida Laraki, and Panayotis Mertikopoulos. Constant regret in general games via higher-order optimism. arXiv preprint arXiv:2609.04113, 2026.arxiv.org/abs/2609.04113
  5. [5]Peter Borwein and Tamás Erdélyi. A sharp Bernstein-type inequality for exponential sums. Journal für die reine und angewandte Mathematik, 476:127–141, 1996.
  6. [6]James P. Bailey and Georgios Piliouras. Multiplicative weights update in zero-sum games. In Proceedings of the ACM Conference on Economics and Computation (EC), 2018.DOI
  7. [7]Noam Brown and Tuomas Sandholm. Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. Science, 359(6374):418–424, 2018.DOI
  8. [8]Nicolò Cesa-Bianchi and Gábor Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006.
  9. [9]Yang Cai, Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo, and Weiqiang Zheng. Fast last-iterate convergence of learning in games requires forgetful algorithms. Advances in Neural Information Processing Systems, 37:23406–23434, 2024.arxiv.org/abs/2406.10631
  10. [10]Xi Chen and Binghui Peng. Hedging in games: Faster convergence of external and swap regrets. In Advances in Neural Information Processing Systems (NeurIPS), 2020.arxiv.org/abs/2006.04953
  11. [11]Chao-Kai Chiang, Tianbao Yang, Chia-Jung Lee, Mehrdad Mahdavi, Chi-Jen Lu, Rong Jin, and Shenghuo Zhu. Online optimization with gradual variations. In Conference on Learning Theory (COLT), 2012.
  12. [12]Constantinos Daskalakis, Alan Deckelbaum, and Anthony Kim. Near-optimal no-regret algorithms for zero-sum games. In Proceedings of the ACM-SIAM Symposium on Discrete Algorithms (SODA), 2011.
  13. [13]Constantinos Daskalakis, Maxwell Fishelson, and Noah Golowich. Near-optimal no-regret learning in general games. In Advances in Neural Information Processing Systems (NeurIPS), 2021. arXiv:2108.06924.arxiv.org/abs/2108.06924
  14. [14]Constantinos Daskalakis and Ioannis Panageas. Last-iterate convergence: Zero-sum games and constrained min-max optimization. In Innovations in Theoretical Computer Science (ITCS), 2019.
  15. [15]Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, and Tuomas Sandholm. Near-optimal no-regret learning dynamics for general convex games. In Advances in Neural Information Processing Systems (NeurIPS), 2022.arxiv.org/abs/2206.08742
  16. [16]Jacques Frisch. Points de platitude d’un morphisme d’espaces analytiques complexes. Inventiones Mathematicae, 4:118–138, 1967.DOI
  17. [17]Yoav Freund and Robert E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1):119–139, 1997.DOI
  18. [18]Yoav Freund and Robert E. Schapire. Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29:79–103, 1999.DOI
  19. [19]Dean P. Foster and Rakesh V. Vohra. Calibrated learning and correlated equilibrium. Games and Economic Behavior, 21:40–55, 1997.
  20. [20]Juns oo Ha. A horizon-independent regret bound for Optimistic Hedge in general-sum games. arXiv preprint arXiv:2609.22839, 2026.arxiv.org/abs/2609.22839
  21. [21]Junsoo Ha. A logarithmic regret bound for Optimistic Hedge in general-sum games. arXiv preprint arXiv:2609.19677, 2026.arxiv.org/abs/2609.19677
  22. [22]James Hannan. Approximation to Bayes risk in repeated play. In Melvin Dresher, Albert W. Tucker, and Philip Wolfe, editors, Contributions to the Theory of Games, Volume III, number 39 in Annals of Mathematics Studies, pages 97–139. Princeton University Press, 1957.
  23. [23]Sergiu Hart and Andreu Mas-Colell. A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68(5):1127–1150, 2000.
  24. [24]Mingyang Liu, Gabriele Farina, and Asuman Ozdaglar. Constant individual regret in general games. arXiv preprint arXiv:2608.31166, 2026.arxiv.org/abs/2608.31166
  25. [25]Nick Littlestone and Manfred K. Warmuth. The weighted majority algorithm. Information and Computation, 108(2):212–261, 1994.
  26. [26]Tung Mai. Constant swap regret in general-sum games via two-scale higher-order optimism. arXiv preprint arXiv:2609.16751, 2026.arxiv.org/abs/2609.16751
  27. [27]Bernard Martinet. Regularisation d’inéquations variationnelles par approximations successives. Revue française d’informatique et de recherche opérationnelle, Série rouge, 4(R3):154–158, 1970.DOI
  28. [28]Aryan Mokhtari, Asuman Ozdaglar, and Sarath Pattathil. A unified analysis of extra-gradient and optimistic gradient methods for saddle point problems: Proximal point approach. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), volume 108 of PMLR, pages 1497–1507, 2020.arxiv.org/abs/1901.08511
  29. [29]Panayotis Mertikopoulos, Christos Papadimitriou, and Georgios Piliouras. Cycles in adversarial regularized learning. In Proceedings of the ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018.arxiv.org/abs/1709.02738
  30. [30]Hervé Moulin and Jean-Philippe Vial. Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon. International Journal of Game Theory, 7(3–4):201–221, 1978.DOI
  31. [31]Denis Nekipelov, Vasilis Syrgkanis, and Éva Tardos. Econometrics for learning agents. In Proceedings of the ACM Conference on Economics and Computation (EC), 2015.
  32. [32]Leonid D. Popov. A modification of the Arrow–Hurwicz method for search of saddle points. Mathematical Notes of the Academy of Sciences of the USSR, 28(5):845–848, 1980.DOI
  33. [33]Georgios Piliouras, Ryann Sim, and Stratis Skoulakis. Beyond time-average convergence: Near-optimal uncoupled online learning via clairvoyant multiplicative weights update. In Advances in Neural Information Processing Systems (NeurIPS), 2022.arxiv.org/abs/2111.14737
  34. [34]R. Tyrrell Rockafellar. Monotone operators and the proximal point algorithm. SIAM Journal on Control and Optimization, 14(5):877–898, 1976.DOI
  35. [35]Alexander Rakhlin and Karthik Sridharan. Online learning with predictable sequences. In Conference on Learning Theory (COLT), 2013.arxiv.org/abs/1208.3728
  36. [36]Alexander Rakhlin and Karthik Sridharan. Optimization, learning, and games with predictable sequences. In Advances in Neural Information Processing Systems (NeurIPS), 2013.arxiv.org/abs/1311.1869
  37. [37]Vasilis Syrgkanis, Alekh Agarwal, Haipeng Luo, and Robert E. Schapire. Fast convergence of regularized learning in games. In Advances in Neural Information Processing Systems (NeurIPS), 2015.arxiv.org/abs/1507.00407
  38. [38]Michael Shub. Global Stability of Dynamical Systems. Springer-Verlag, 1987.DOI
  39. [39]Ashkan Soleymani and Georgios Piliouras. Multiplicative optimism for constant regret in games. arXiv preprint arXiv:2609.21976, 2026.arxiv.org/abs/2609.21976
  40. [40]Ashkan Soleymani, Georgios Piliouras, and Gabriele Farina. Faster rates for no-regret learning in general games via cautious optimism. In Proceedings of the ACM Symposium on Theory of Computing (STOC), 2025. arXiv:2503.24340.DOI
  41. [41]Gábor Szegő. Orthogonal Polynomials. American Mathematical Society, 4th edition, 1975.
  42. [42]Taira Tsuchiya. Tight regret upper and lower bounds for Optimistic Hedge in two-player zero-sum games. In Proceedings of the 29th International Conference on Artificial Intelligence and Statistics, volume 300 of Proceedings of Machine Learning Research, pages 4870–4878, 2026.arxiv.org/abs/2510.11691
  43. [43]Chen-Yu Wei, Chung-Wei Lee, Mengxiao Zhang, and Haipeng Luo. Linear last-iterate convergence in constrained saddle-point optimization. In International Conference on Learning Representations (ICLR), 2021.arxiv.org/abs/2006.09517
  44. [44]Martin Zinkevich, Michael Johanson, Michael Bowling, and Carmelo Piccione. Regret minimization in games with incomplete information. In Advances in Neural Information Processing Systems (NeurIPS), 2007.DOI

Paper details

vlnc:W_kqukdc9y
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 8

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

OpenAI’s ChatGPT, Claude

View statement
Looking for related papers…
Contents