Acrobot
9 papers with code • 0 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.
Benchmarks
These leaderboards are used to track progress in Acrobot
Latest papers with no code
Learning sparse representations in reinforcement learning
This has motivated methods that learn internal representations of the agent's state, effectively reducing the size of the state space and restructuring state representations in order to support generalization.
Deterministic Policy Optimization by Combining Pathwise and Score Function Estimators for Discrete Action Spaces
Our method is applicable to both discrete and continuous action spaces, when competing pathwise methods are limited to the latter.