相关论文: Fast Population-Based Reinforcement Learning on a …
Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language…
Training machine learning algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from costly…
Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a…
While reinforcement learning has made great improvements, state-of-the-art algorithms can still struggle with seemingly simple set-point feedback control problems. One reason for this is that the learned controller may not be able to excite…
Learning from human demonstrations (behavior cloning) is a cornerstone of robot learning. However, most behavior cloning algorithms require a large number of demonstrations to learn a task, especially for general tasks that have a large…
While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural…
We present an end-to-end framework for the Assignment Problem with multiple tasks mapped to a group of workers, using reinforcement learning while preserving many constraints. Tasks and workers have time constraints and there is a cost…
Driving in dense traffic with human and autonomous drivers is a challenging task that requires high-level planning and reasoning. Human drivers can achieve this task comfortably, and there has been many efforts to model human driver…
Population protocols are a distributed computing model appropriate for describing massive numbers of agents with limited computational power. A population protocol "has an initial leader" if every valid initial configuration contains a…
Despite the potential of reinforcement learning (RL) for building general-purpose robotic systems, training RL agents to solve robotics tasks still remains challenging due to the difficulty of exploration in purely continuous action spaces.…
Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads…
The effects of policy sharing between agents in a multi-agent dynamical system has not been studied extensively. I simulate a system of agents optimizing the same task using reinforcement learning, to study the effects of different…
We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…
Bimodal, stochastic environments present a challenge to typical Reinforcement Learning problems. This problem is one that is surprisingly common in real world applications, being particularly applicable to pricing problems. In this paper we…
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based…
Fine tuning distributed systems is considered to be a craftsmanship, relying on intuition and experience. This becomes even more challenging when the systems need to react in near real time, as streaming engines have to do to maintain…
Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…
Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small…
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…
Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…