Reinforcement Learning
A State Representation for Diminishing Rewards
In such situations, the successor representation (SR) is a popular framework which supports rapid policy evaluation by decoupling a policy's
Large Language Models Can Implement Policy Iteration Ethan Brooks 1, Logan Walls 2, Richard L. Lewis
Gradient techniques are inherently slow, sacrificing the "few-shot" quality
Overleaf Example
Second, we enforce the posterior update model to learn the dynamics of the latent variable.
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
In the standard reinforcement learning (RL) setting, the primary goal is to obtain a policy that maximizes a cumulative scalar reward [Sutton and Barto, 2018].
Safety through feedback in Constrained RL
This feedback can be system generated or elicited from a human observing the training process. Previous approaches have not been able to scale to complex environments and are constrained to receiving feedback at the state level which can be expensive to collect. To this end, we introduce an approach that scales to more complex domains and extends beyond state-level feedback, thus, reducing the burden on the evaluator.
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
This paper proceeds as follows.