-
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinf...
Three simulated tasks and a challenging real-world robotic insertion task. -
Robot Grasping Dataset
The dataset used in this paper is a robot grasping dataset, where the robot learns to grasp objects in a simulated environment. -
Data Informed Residual Reinforcement Learning for High-Dimensional Robotic Tr...
The dataset used in the paper is a high-dimensional robotic tracking control task. -
HalfCheetah and Walker2d
The dataset used in the paper is the HalfCheetah and Walker2d environments from the D4RL dataset. -
Autonomous Reinforcement Learning of Multiple Interrelated Tasks
The dataset used in the paper is a simulated robotic scenario involving multiple interrelated tasks. -
Scripted pick and place policy
Scripted pick and place policy -
Scripted grasping policy
Scripted grasping policy -
Task-specific data
Task-specific data -
Prior dataTask data
Prior dataTask data -
Cassie Dataset
The dataset used in this paper is a closed-loop system of a bipedal robot Cassie controlled by a model-free reinforcement learning (RL) policy. -
Multi-goal Reach Task Dataset
The dataset used in the paper is a multi-goal reach task dataset, where the robot arm needs to reach a target pose with varying precision requirements. -
Minigrid environment
The dataset used in the paper is the Minigrid environment, which is a 3D grid world with a goal at the bottom-right corner. The agent learns to navigate to the goal using human... -
Target Stacking
A synthetic block stacking environment with physics simulation in which the agent can learn block stacking end-to-end through trial and error, bypassing to explicitly model the... -
2D Environment
The dataset used in the paper is a 2D environment where experiments are done. -
MuJoCo Environment
The dataset used in the paper is a MuJoCo environment, with 13-states and 4-control inputs, nonlinear dynamics with polynomial dependency in the control inputs. -
Guard: A safe reinforcement learning benchmark
The dataset used in the paper is a collection of robot locomotion tasks with various constraints. -
Pretrained Visual Representations in Reinforcement Learning
Visual reinforcement learning (RL) has made significant progress in recent years, but the choice of visual feature extractor remains a crucial design decision.
