Picture for Jose A. Arjona-Medina

Jose A. Arjona-Medina

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Add code
Sep 29, 2020
Figure 1 for Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Figure 2 for Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Figure 3 for Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Figure 4 for Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
Viaarxiv icon

Explaining and Interpreting LSTMs

Add code
Sep 25, 2019
Figure 1 for Explaining and Interpreting LSTMs
Figure 2 for Explaining and Interpreting LSTMs
Figure 3 for Explaining and Interpreting LSTMs
Figure 4 for Explaining and Interpreting LSTMs
Viaarxiv icon

RUDDER: Return Decomposition for Delayed Rewards

Add code
Jun 20, 2018
Figure 1 for RUDDER: Return Decomposition for Delayed Rewards
Figure 2 for RUDDER: Return Decomposition for Delayed Rewards
Figure 3 for RUDDER: Return Decomposition for Delayed Rewards
Figure 4 for RUDDER: Return Decomposition for Delayed Rewards
Viaarxiv icon