Related papers: ProSpec RL: Plan Ahead, then Execute
Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for…
In this paper, we propose ProRAC (Progression-based Reasoning about Actions and Change), a neuro-symbolic framework that leverages LLMs to tackle RAC problems. ProRAC extracts fundamental RAC elements including actions and questions from…
Recent works have shown that sequence modeling can be effectively used to train reinforcement learning (RL) policies. However, the success of applying existing sequence models to planning, in which we wish to obtain a trajectory of actions…
Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effects of an agent's possible actions. When no such model is…
Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…
The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs…
We study online fine-tuning of pretrained control policies for autonomous driving using Real-Time Recurrent Reinforcement Learning (RTRRL), a memory-efficient algorithm that updates policy parameters at every time step without…
As machine learning has moved towards leveraging large models as priors for downstream tasks, the community has debated the right form of prior for solving reinforcement learning (RL) problems. If one were to try to prefetch as much…
Prospection, the act of predicting the consequences of many possible futures, is intrinsic to human planning and action, and may even be at the root of consciousness. Surprisingly, this idea has been explored comparatively little in…
Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large datasets have achieved success, there is often a need to…
Traditional model-based reinforcement learning (RL) methods generate forward rollout traces using the learnt dynamics model to reduce interactions with the real environment. The recent model-based RL method considers the way to learn a…
Existing Large Language Model (LLM) agents struggle in interactive environments requiring long-horizon planning, primarily due to compounding errors when simulating future states. To address this, we propose ProAct, a framework that enables…
Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…
Modern cyber-physical systems are becoming increasingly complex to model, thus motivating data-driven techniques such as reinforcement learning (RL) to find appropriate control agents. However, most systems are subject to hard constraints…
Standard reinforcement learning (RL) optimizes policies for reward but imposes few constraints on how decisions evolve over time. As a result, policies may achieve high performance while exhibiting temporally incoherent behavior such as…
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware…
This paper proposes a novel deep reinforcement learning (RL) architecture, called Value Prediction Network (VPN), which integrates model-free and model-based RL methods into a single neural network. In contrast to typical model-based RL…
Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with their environments to learn effectively. These limitations…
Reinforcement learning (RL) is a promising tool to solve robust optimal well control problems where the model parameters are highly uncertain, and the system is partially observable in practice. However, RL of robust control policies often…