Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge to accelerate policy learning for RL processes. However, we note that such guidance is often tailored for one specific task but loses generalizability. In this paper, we introduce a framework that harnesses LLMs to extract background knowledge of an environment, which contains general understandings of the entire environment, making various downstream RL tasks benefit from one-time knowledge representation. We ground LLMs by feeding a few pre-collected experiences and requesting them to delineate background knowledge of the environment. Afterward, we represent the output knowledge as potential functions for potential-based reward shaping, which has a good property for maintaining policy optimality from task rewards. We instantiate three variants to prompt LLMs for background knowledge, including writing code, annotating preferences, and assigning goals. Our experiments show that these methods achieve significant sample efficiency improvements in a spectrum of downstream tasks from Minigrid and Crafter domains.

An Autonomous Large Language Model Agent for Chemical Literature Data Mining

Chemical synthesis, which is crucial for advancing material synthesis and drug discovery, impacts various sectors including environmental science and healthcare. The rise of technology in chemistry has generated extensive chemical data, challenging researchers to discern patterns and refine synthesis processes. Artificial intelligence (AI) helps by analyzing data to optimize synthesis and increase yields. However, AI faces challenges in processing literature data due to the unstructured format and diverse writing style of chemical literature. To overcome these difficulties, we introduce an end-to-end AI agent framework capable of high-fidelity extraction from extensive chemical literature. This AI agent employs large language models (LLMs) for prompt generation and iterative optimization. It functions as a chemistry assistant, automating data collection and analysis, thereby saving manpower and enhancing performance. Our framework's efficacy is evaluated using accuracy, recall, and F1 score of reaction condition data, and we compared our method with human experts in terms of content correctness and time efficiency. The proposed approach marks a significant advancement in automating chemical literature extraction and demonstrates the potential for AI to revolutionize data management and utilization in chemistry.

More Agents Is All You Need

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: \url{https://anonymous.4open.science/r/more_agent_is_all_you_need}.

Affordable Generative Agents

The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents. However, the substantial cost on maintaining the prolonged agent interactions poses challenge over the deployment of believable LLM-based agents. Therefore, in this paper, we develop Affordable Generative Agents (AGA), a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels. Specifically, for agent-environment interactions, we substitute repetitive LLM inferences with learned policies; while for inter-agent interactions, we model the social relationships between agents and compress auxiliary dialogue information. Extensive experiments on multiple environments show the effectiveness and efficiency of our proposed framework. Also, we delve into the mechanisms of emergent believable behaviors lying in LLM agents, demonstrating that agents can only generate finite behaviors in fixed environments, based upon which, we understand ways to facilitate emergent interaction behaviors. Our code is publicly available at: \url{https://github.com/AffordableGenerativeAgents/Affordable-Generative-Agents}.

Towards an Automatic AI Agent for Reaction Condition Recommendation in Chemical Synthesis

Artificial intelligence (AI) for reaction condition optimization has become an important topic in the pharmaceutical industry, given that a data-driven AI model can assist drug discovery and accelerate reaction design. However, existing AI models lack the chemical insights and real-time knowledge acquisition abilities of experienced human chemists. This paper proposes a Large Language Model (LLM) empowered AI agent to bridge this gap. We put forth a novel three-phase paradigm and applied advanced intelligence-enhancement methods like in-context learning and multi-LLM debate so that the AI agent can borrow human insight and update its knowledge by searching the latest chemical literature. Additionally, we introduce a novel Coarse-label Contrastive Learning (CCL) based chemical fingerprint that greatly enhances the agent's performance in optimizing the reaction condition. With the above efforts, the proposed AI agent can autonomously generate the optimal reaction condition recommendation without any human interaction. Further, the agent is highly professional in terms of chemical reactions. It demonstrates close-to-human performance and strong generalization capability in both dry-lab and wet-lab experiments. As the first attempt in the chemical AI agent, this work goes a step further in the field of "AI for chemistry" and opens up new possibilities for computer-aided synthesis planning.

Pretraining in Deep Reinforcement Learning: A Survey

The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning. Various breakthroughs ranging from games to robotics have spurred the interest in designing sophisticated RL algorithms and systems. However, the prevailing workflow in RL is to learn tabula rasa, which may incur computational inefficiency. This precludes continuous deployment of RL algorithms and potentially excludes researchers without large-scale computing resources. In many other areas of machine learning, the pretraining paradigm has shown to be effective in acquiring transferable knowledge, which can be utilized for a variety of downstream tasks. Recently, we saw a surge of interest in Pretraining for Deep RL with promising results. However, much of the research has been based on different experimental settings. Due to the nature of RL, pretraining in this field is faced with unique challenges and hence requires new design principles. In this survey, we seek to systematically review existing works in pretraining for deep reinforcement learning, provide a taxonomy of these methods, discuss each sub-field, and bring attention to open problems and future directions.

Revisiting Discrete Soft Actor-Critic

We study the adaption of soft actor-critic (SAC) from continuous action space to discrete action space. We revisit vanilla SAC and provide an in-depth understanding of its Q value underestimation and performance instability issues when applied to discrete settings. We thereby propose entropy-penalty and double average Q-learning with Q-clip to address these issues. Extensive experiments on typical benchmarks with discrete action space, including Atari games and a large-scale MOBA game, show the efficacy of our proposed method. Our code is at:https://github.com/coldsummerday/Revisiting-Discrete-SAC.

MetaRF: Differentiable Random Forest for Reaction Yield Prediction with a Few Trails

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield prediction problem, which assists chemists in selecting high-yield reactions in a new chemical space only with a few experimental trials. To attack this challenge, we first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction, where the attention weight of a random forest is automatically optimized by the meta-learning framework and can be quickly adapted to predict the performance of new reagents while given a few additional samples. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method to determine valuable samples to be experimentally tested and then learned. Our methodology is evaluated on three different datasets and acquires satisfactory performance on few-shot prediction. In high-throughput experimentation (HTE) datasets, the average yield of our methodology's top 10 high-yield reactions is relatively close to the results of ideal yield selection.

MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost -- increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve each sub-task. To boost the learning of sub-tasks, we propose a combination of techniques including 1) action-aware representation learning which captures underlying relations between action and representation, 2) discriminator-based self-imitation learning for efficient exploration, and 3) ensemble behavior cloning with consistency filtering for policy robustness. Extensive experiments show that JueWu-MC significantly improves sample efficiency and outperforms a set of baselines by a large margin. Notably, we won the championship of the NeurIPS MineRL 2021 research competition and achieved the highest performance score ever.