| 1. |
- Carlsson, Emil, 1995
(författare)
-
Efficient Communication via Reinforcement Learning
- 2022
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication. This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load. In this thesis we combine the information-theoretic perspective on language with recent advances in deep multi-agent reinforcement learning. We explore how efficient communication emerges between two artificial agents in a signaling game as a by-product of them maximizing a shared reward signal. This is tested in the domain of colors and numeral systems, two domains in which human languages tends to support efficient communication. We find that the communication developed by the artificial agents in these domains shares characteristics with human languages when it comes to efficiency and structure of semantic partitions. even though the agents lack the full perceptual and linguistic architecture of humans. Our results offer a computational learning perspective that may complement the information-theoretic view on the structure of human languages. The results also suggests that reinforcement learning is a powerful and flexible framework that can be used to test and generate hypotheses in silico.
|
|
| 2. |
- Carlsson, Emil, 1995, et al.
(författare)
-
Learning Approximate and Exact Numeral Systems via Reinforcement Learning
- 2021
-
Ingår i: Proceedings of the 43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021. ; 43
-
Konferensbidrag (refereegranskat)abstract
- Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how efficient communication emerges via reinforcement learning. In our framework, two artificial agents play a Lewis signaling game where the goal is to convey a numeral concept. The agents gradually learn to communicate using reinforcement learning and the resulting numeral systems are shown to be efficient in the information-theoretic framework of Regier et al.(2015); Gibson et al. (2017). They are also shown to be similar to human numeral systems of same type. Our results thus provide a mechanistic explanation via reinforcement learning of the recent results in Xu et al. (2020) and can potentially be generalized to other semantic domains.
|
|
| 3. |
- Carlsson, Emil, 1995, et al.
(författare)
-
Pragmatic Reasoning in Structured Signaling Games
- 2022
-
Ingår i: Proceedings of the 44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022. ; , s. 2831-2837
-
Konferensbidrag (refereegranskat)abstract
- In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) framework which we call structured-RSA (sRSA) for pragmatic reasoning in structured domains. We explore the behavior of the sRSA in the domain of color and show that pragmatic agents using sRSA on top of semantic representations, derived from the World Color Survey, attain efficiency very close to the information theoretic limit after only 1 or 2 levels of recursion. We also explore the interaction between pragmatic reasoning and learning in multi-agent reinforcement learning framework. Our results illustrate that artificial agents using sRSA develop communication closer to the information theoretic frontier compared to agents using RSA and just reinforcement learning. We also find that the ambiguity of the semantic representation increases as the pragmatic agents are allowed to perform deeper reasoning about each other during learning.
|
|
| 4. |
- Carlsson, Emil, 1995, et al.
(författare)
-
Pure Exploration in Bandits with Linear Constraints
- 2024
-
Ingår i: Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence, UAI 2022. - 2640-3498. ; 238, s. 334-342
-
Konferensbidrag (refereegranskat)abstract
- We address the problem of identifying the optimal policy with a fixed confidence level in a multi-armed bandit setup, when the arms are subject to linear constraints. Unlike the standard best-arm identification problem which is well studied, the optimal policy in this case may not be deterministic and could mix between several arms. This changes the geometry of the problem which we characterize via an information-theoretic lower bound. We introduce two asymptotically optimal algorithms for this setting, one based on the Track-and-Stop method and the other based on a game-theoretic approach. Both these algorithms try to track an optimal allocation based on the lower bound and computed by a weighted projection onto the boundary of a normal cone. Finally, we provide empirical results that validate our bounds and visualize how constraints change the hardness of the problem.
|
|
| 5. |
- Carlsson, Emil, 1995, et al.
(författare)
-
Thompson Sampling for Bandits with Clustered Arms
- 2021
-
Ingår i: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. - California : International Joint Conferences on Artificial Intelligence Organization. - 9780999241196
-
Konferensbidrag (refereegranskat)abstract
- We propose algorithms based on a multi-level Thompson sampling scheme, for the stochastic multi-armed bandit and its contextual variant with linear expected rewards, in the setting where arms are clustered. We show, both theoretically and empirically, how exploiting a given cluster structure can significantly improve the regret and computational cost compared to using standard Thompson sampling. In the case of the stochastic multi-armed bandit we give upper bounds on the expected cumulative regret showing how it depends on the quality of the clustering. Finally, we perform an empirical evaluation showing that our algorithms perform well compared to previously proposed algorithms for bandits with clustered arms.
|
|
| 6. |
- Jergéus, Erik, et al.
(författare)
-
Towards Learning Abstractions via Reinforcement Learning
- 2022
-
Ingår i: CEUR Workshop Proceedings. - 1613-0073. ; 3400, s. 120-126
-
Konferensbidrag (refereegranskat)abstract
- In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is referred to as a neuro-symbolic system. The agents are not restricted to only use initial primitives: reinforcement learning is interleaved with steps to extend the current language with novel higher-level concepts, allowing generalisation and more informative communication via shorter messages. We demonstrate that this approach allow agents to converge more quickly on a small collaborative construction task.
|
|
| 7. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
A reinforcement-learning approach to efficient communication
- 2020
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 15:7
-
Tidskriftsartikel (refereegranskat)abstract
- We present a multi-agent computational approach to partitioning semantic spaces using reinforcement-learning (RL). Two agents communicate using a finite linguistic vocabulary in order to convey a concept. This is tested in the color domain, and a natural reinforcement learning mechanism is shown to converge to a scheme that achieves a near-optimal trade-off of simplicity versus communication efficiency. Results are presented both on the communication efficiency as well as on analyses of the resulting partitions of the color space. The effect of varying environmental factors such as noise is also studied. These results suggest that RL offers a powerful and flexible computational framework that can contribute to the development of communication schemes for color names that are near-optimal in an information-theoretic sense and may shape color-naming systems across languages. Our approach is not specific to color and can be used to explore cross-language variation in other semantic domains.
|
|
