Picture for Tom J. Ameloot

Tom J. Ameloot

Learning with Value-Ramp

Add code
Apr 23, 2017
Figure 1 for Learning with Value-Ramp
Figure 2 for Learning with Value-Ramp
Figure 3 for Learning with Value-Ramp
Figure 4 for Learning with Value-Ramp
Viaarxiv icon

On Avoidance Learning with Partial Observability

Add code
May 16, 2016
Figure 1 for On Avoidance Learning with Partial Observability
Figure 2 for On Avoidance Learning with Partial Observability
Figure 3 for On Avoidance Learning with Partial Observability
Figure 4 for On Avoidance Learning with Partial Observability
Viaarxiv icon

On the convergence of cycle detection for navigational reinforcement learning

Add code
Jan 05, 2016
Figure 1 for On the convergence of cycle detection for navigational reinforcement learning
Figure 2 for On the convergence of cycle detection for navigational reinforcement learning
Figure 3 for On the convergence of cycle detection for navigational reinforcement learning
Figure 4 for On the convergence of cycle detection for navigational reinforcement learning
Viaarxiv icon

Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors

Add code
Dec 01, 2015
Viaarxiv icon