5 papers with code • 1 benchmarks • 0 datasets
The acrobot system includes two joints and two links, where the joint between the two links is actuated. Initially, the links are hanging downwards, and the goal is to swing the end of the lower link up to a given height.
We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime.
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning.
We contribute to model-based micro-data reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent.
Ranked #1 on Acrobot on .
This paper outlines a methodological approach for designing adaptive agents driving themselves near points of criticality.
In order to explore how criticality might emerge from general adaptive mechanisms, we propose a simple learning rule that maintains an internal organizational structure from a specific family of systems at criticality.