SOTAVerified

Acrobot

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.

Papers

Showing 1120 of 28 papers

TitleStatusHype
KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images0
LagNetViP: A Lagrangian Neural Network for Video Prediction0
Learning Environment Models with Continuous Stochastic Dynamics0
Learning global control of underactuated systems with Model-Based Reinforcement Learning0
Learning sparse representations in reinforcement learning0
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces0
Linear Function Approximation as a Computationally Efficient Method to Solve Classical Reinforcement Learning Challenges0
Bellman operator convergence enhancements in reinforcement learning algorithms0
BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies0
Online Attentive Kernel-Based Temporal Difference Learning0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.