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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 28 papers

TitleStatusHype
Meta-learning curiosity algorithmsCode1
Transfer Reinforcement Learning for Differing Action Spaces via Q-Network RepresentationsCode1
Learning Synthetic Environments for Reinforcement Learning with Evolution StrategiesCode1
RobotDiffuse: Motion Planning for Redundant Manipulator based on Diffusion ModelCode1
Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?Code1
Adaptation to criticality through organizational invariance in embodied agentsCode0
Adaptive Online Value Function Approximation with WaveletsCode0
Criticality as It Could Be: organizational invariance as self-organized criticality in embodied agentsCode0
Signal Novelty Detection as an Intrinsic Reward for RoboticsCode0
Total energy-shaping control for mechanical systems via Control-by-InterconnectionCode0
KeyCLD: Learning Constrained Lagrangian Dynamics in Keypoint Coordinates from Images—0
LagNetViP: A Lagrangian Neural Network for Video Prediction—0
Learning Environment Models with Continuous Stochastic Dynamics—0
Learning global control of underactuated systems with Model-Based Reinforcement Learning—0
Learning sparse representations in reinforcement learning—0
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces—0
Linear Function Approximation as a Computationally Efficient Method to Solve Classical Reinforcement Learning Challenges—0
Bellman operator convergence enhancements in reinforcement learning algorithms—0
BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies—0
Online Attentive Kernel-Based Temporal Difference Learning—0
Real-Time Model Predictive Control for the Swing-Up Problem of an Underactuated Double Pendulum—0
Robot Design With Neural Networks, MILP Solvers and Active Learning—0
Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks—0
A Neuromorphic Architecture for Reinforcement Learning from Real-Valued Observations—0
Solving the swing-up and balance task for the Acrobot and Pendubot with SAC—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.