Marlos C. Machado and colleagues, 2017
We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE.
Don't Just Read it – Explore It
We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE.
We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic.
This paper examines six extensions to the DQN algorithm and empirically studies their combination.
We present DrQ-v2, a model-free reinforcement learning algorithm for visual continuous control.
MuZero learns a model that, when applied iteratively, predicts the quantities most directly relevant to planning.
We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination.
In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks.
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
In this paper we investigate if, and how, grounded compositional language can emerge as a means to achieve goals in multi-agent populations.
To bridge this gap, we introduce ToolLLM, a general tool-use framework encompassing data construction, model training, and evaluation.
To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing.
We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls.