Designing and deriving effective model-based reinforcement learning (MBRL) algorithms
with a performance improvement guarantee is challenging, mainly attributed to the high …

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents'
behavior with human desired outcomes, but is often restrained by costly human feedback …

Dyna-style model-based reinforcement learning contains two phases: model rollouts to
generate sample for policy learning and real environment exploration using current policy …

In model-based reinforcement learning, the conventional approach to addressing world
model bias is to use gradient optimization methods. However, using a singular policy from …

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of
the environment to all past experience, but this wastes model capacity on data that is …

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient,
adaptive, and explainable by learning an explicit model of the environment. While the …

The primacy bias in deep reinforcement learning (DRL), which refers to the agent's tendency
to overfit early data and lose the ability to learn from new data, can significantly decrease the …

Abstract Model-based reinforcement learning (RL) has demonstrated remarkable successes
on a range of continuous control tasks due to its high sample efficiency. To save the …

Large language models (LLMs) have significantly advanced various natural language
processing tasks, but deploying them remains computationally expensive. Knowledge …

Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for
enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have …