Picture for Daniel Graves

Daniel Graves

Learning robust driving policies without online exploration

Add code
Mar 15, 2021
Figure 1 for Learning robust driving policies without online exploration
Figure 2 for Learning robust driving policies without online exploration
Figure 3 for Learning robust driving policies without online exploration
Figure 4 for Learning robust driving policies without online exploration
Viaarxiv icon

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems

Add code
Feb 16, 2021
Viaarxiv icon

LISPR: An Options Framework for Policy Reuse with Reinforcement Learning

Add code
Dec 29, 2020
Figure 1 for LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Figure 2 for LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Figure 3 for LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Figure 4 for LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Viaarxiv icon

Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning

Add code
Nov 11, 2020
Figure 1 for Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning
Figure 2 for Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning
Figure 3 for Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning
Figure 4 for Offline Learning of Counterfactual Perception as Prediction for Real-World Robotic Reinforcement Learning
Viaarxiv icon

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving

Add code
Nov 01, 2020
Figure 1 for SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
Figure 2 for SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
Figure 3 for SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
Figure 4 for SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
Viaarxiv icon

Affordance as general value function: A computational model

Add code
Oct 27, 2020
Figure 1 for Affordance as general value function: A computational model
Figure 2 for Affordance as general value function: A computational model
Figure 3 for Affordance as general value function: A computational model
Figure 4 for Affordance as general value function: A computational model
Viaarxiv icon

What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator

Add code
Oct 19, 2020
Figure 1 for What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
Figure 2 for What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
Figure 3 for What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
Figure 4 for What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
Viaarxiv icon

Learning predictive representations in autonomous driving to improve deep reinforcement learning

Add code
Jun 26, 2020
Figure 1 for Learning predictive representations in autonomous driving to improve deep reinforcement learning
Figure 2 for Learning predictive representations in autonomous driving to improve deep reinforcement learning
Figure 3 for Learning predictive representations in autonomous driving to improve deep reinforcement learning
Figure 4 for Learning predictive representations in autonomous driving to improve deep reinforcement learning
Viaarxiv icon

Perception as prediction using general value functions in autonomous driving applications

Add code
Jan 24, 2020
Figure 1 for Perception as prediction using general value functions in autonomous driving applications
Figure 2 for Perception as prediction using general value functions in autonomous driving applications
Figure 3 for Perception as prediction using general value functions in autonomous driving applications
Figure 4 for Perception as prediction using general value functions in autonomous driving applications
Viaarxiv icon

Efficient decorrelation of features using Gramian in Reinforcement Learning

Add code
Nov 19, 2019
Figure 1 for Efficient decorrelation of features using Gramian in Reinforcement Learning
Figure 2 for Efficient decorrelation of features using Gramian in Reinforcement Learning
Figure 3 for Efficient decorrelation of features using Gramian in Reinforcement Learning
Figure 4 for Efficient decorrelation of features using Gramian in Reinforcement Learning
Viaarxiv icon