Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop context-aware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios. The code is publicly available at https://github.com/LXXXXR/CACOM.

The performance of Markov chain Monte Carlo samplers strongly depends on the properties of the target distribution such as its covariance structure, the location of its probability mass and its tail behavior. We explore the use of bijective affine transformations of the sample space to improve the properties of the target distribution and thereby the performance of samplers running in the transformed space. In particular, we propose a flexible and user-friendly scheme for adaptively learning the affine transformation during sampling. Moreover, the combination of our scheme with Gibbsian polar slice sampling is shown to produce samples of high quality at comparatively low computational cost in several settings based on real-world data.

Simulating sampling algorithms with people has proven a useful method for efficiently probing and understanding their mental representations. We propose that the same methods can be used to study the representations of Large Language Models (LLMs). While one can always directly prompt either humans or LLMs to disclose their mental representations introspectively, we show that increased efficiency can be achieved by using LLMs as elements of a sampling algorithm. We explore the extent to which we recover human-like representations when LLMs are interrogated with Direct Sampling and Markov chain Monte Carlo (MCMC). We found a significant increase in efficiency and performance using adaptive sampling algorithms based on MCMC. We also highlight the potential of our method to yield a more general method of conducting Bayesian inference \textit{with} LLMs.

The remote wireless control of industrial systems is one of the major use cases for 5G and beyond systems: in these cases, the massive amounts of sensory information that need to be shared over the wireless medium may overload even high-capacity connections. Consequently, solving the effective communication problem by optimizing the transmission strategy to discard irrelevant information can provide a significant advantage, but is often a very complex task. In this work, we consider a prototypal system in which an observer must communicate its sensory data to a robot controlling a task (e.g., a mobile robot in a factory). We then model it as a remote Partially Observable Markov Decision Process (POMDP), considering the effect of adopting semantic and effective communication-oriented solutions on the overall system performance. We split the communication problem by considering an ensemble Vector Quantized Variational Autoencoder (VQ-VAE) encoding, and train a Deep Reinforcement Learning (DRL) agent to dynamically adapt the quantization level, considering both the current state of the environment and the memory of past messages. We tested the proposed approach on the well-known CartPole reference control problem, obtaining a significant performance increase over traditional approaches.

Animals often demonstrate a remarkable ability to adapt to their environments during their lifetime. They do so partly due to the evolution of morphological and neural structures. These structures capture features of environments shared between generations to bias and speed up lifetime learning. In this work, we propose a computational model for studying a mechanism that can enable such a process. We adopt a computational framework based on meta reinforcement learning as a model of the interplay between evolution and development. At the evolutionary scale, we evolve reservoirs, a family of recurrent neural networks that differ from conventional networks in that one optimizes not the synaptic weights, but hyperparameters controlling macro-level properties of the resulting network architecture. At the developmental scale, we employ these evolved reservoirs to facilitate the learning of a behavioral policy through Reinforcement Learning (RL). Within an RL agent, a reservoir encodes the environment state before providing it to an action policy. We evaluate our approach on several 2D and 3D simulated environments. Our results show that the evolution of reservoirs can improve the learning of diverse challenging tasks. We study in particular three hypotheses: the use of an architecture combining reservoirs and reinforcement learning could enable (1) solving tasks with partial observability, (2) generating oscillatory dynamics that facilitate the learning of locomotion tasks, and (3) facilitating the generalization of learned behaviors to new tasks unknown during the evolution phase.

Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions, which may cause learning inefficiencies if important environmental changes take many steps to manifest. We propose Hierarchical $k$-Step Latent (HKSL), an auxiliary task that learns multiple representations via a hierarchy of forward models that learn to communicate and an ensemble of $n$-step critics that all operate at varying magnitudes of step skipping. We evaluate HKSL in a suite of 30 robotic control tasks with and without distractors and a task of our creation. We find that HKSL either converges to higher or optimal episodic returns more quickly than several alternative representation learning approaches. Furthermore, we find that HKSL's representations capture task-relevant details accurately across timescales (even in the presence of distractors) and that communication channels between hierarchy levels organize information based on both sides of the communication process, both of which improve sample efficiency.

Existing game AI research mainly focuses on enhancing agents' abilities to win games, but this does not inherently make humans have a better experience when collaborating with these agents. For example, agents may dominate the collaboration and exhibit unintended or detrimental behaviors, leading to poor experiences for their human partners. In other words, most game AI agents are modeled in a "self-centered" manner. In this paper, we propose a "human-centered" modeling scheme for collaborative agents that aims to enhance the experience of humans. Specifically, we model the experience of humans as the goals they expect to achieve during the task. We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e.g., winning games). To achieve this, we propose the Reinforcement Learning from Human Gain (RLHG) approach. The RLHG approach introduces a "baseline", which corresponds to the extent to which humans primitively achieve their goals, and encourages agents to learn behaviors that can effectively enhance humans in achieving their goals better. We evaluate the RLHG agent in the popular Multi-player Online Battle Arena (MOBA) game, Honor of Kings, by conducting real-world human-agent tests. Both objective performance and subjective preference results show that the RLHG agent provides participants better gaming experience.

This paper studies the synergy of solar-battery energy storage system (BESS) and develops a viable strategy for the BESS to unlock its economic potential by serving as a backup to reduce solar curtailments while also participating in the electricity market. We model the real-time bidding of the solar-battery system as two Markov decision processes for the solar farm and the BESS, respectively. We develop a novel deep reinforcement learning (DRL) algorithm to solve the problem by leveraging attention mechanism (AC) and multi-grained feature convolution to process DRL input for better bidding decisions. Simulation results demonstrate that our AC-DRL outperforms two optimization-based and one DRL-based benchmarks by generating 23%, 20%, and 11% higher revenue, as well as improving curtailment responses. The excess solar generation can effectively charge the BESS to bid in the market, significantly reducing solar curtailments by 76% and creating synergy for the solar-battery system to be more viable.

TD learning is the most widely studied algorithm for evaluating the performance of a given policy from data in Markov Decision Processes[1]. The convergence of TD learning with decaying stepsizes was proved in [2]. Over the last few years, there has been a resurgent interest in understanding the non-asymptotic convergence behavior of TD learning and further using it to study other other reinforcement algorithms which use TD learning within their framework. The first result of this type was obtained in [3] who used a projection step in their version of the TD learning algorithm. The first finite-time bounds for unprojected TD learning were obtained in [4], who studied both fixed step-sizes and decaying step-sizes.

An intelligent driving system should be capable of dynamically formulating appropriate driving strategies based on the current environment and vehicle status, while ensuring the security and reliability of the system. However, existing methods based on reinforcement learning and imitation learning suffer from low safety, poor generalization, and inefficient sampling. Additionally, they cannot accurately predict future driving trajectories, and the accurate prediction of future driving trajectories is a precondition for making optimal decisions. To solve these problems, in this paper, we introduce a Safe and Generalized end-to-end Autonomous Driving System (SGADS) for complex and various scenarios. Our SGADS incorporates variational inference with normalizing flows, enabling the intelligent vehicle to accurately predict future driving trajectories. Moreover, we propose the formulation of robust safety constraints. Furthermore, we combine reinforcement learning with demonstrations to augment search process of the agent. The experimental results demonstrate that our SGADS can significantly improve safety performance, exhibit strong generalization, and enhance the training efficiency of intelligent vehicles in complex urban scenarios compared to existing methods.