Picture for Denis Steckelmacher

Denis Steckelmacher

Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution

Add code
Oct 29, 2024
Viaarxiv icon

Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth

Add code
Jun 16, 2023
Figure 1 for Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Figure 2 for Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Figure 3 for Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Figure 4 for Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth
Viaarxiv icon

Transferring Multiple Policies to Hotstart Reinforcement Learning in an Air Compressor Management Problem

Add code
Jan 30, 2023
Viaarxiv icon

Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning

Add code
Jun 10, 2021
Figure 1 for Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Figure 2 for Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Figure 3 for Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning
Viaarxiv icon

Transfer Learning Across Simulated Robots With Different Sensors

Add code
Jul 18, 2019
Figure 1 for Transfer Learning Across Simulated Robots With Different Sensors
Figure 2 for Transfer Learning Across Simulated Robots With Different Sensors
Viaarxiv icon

Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics

Add code
Mar 11, 2019
Figure 1 for Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
Figure 2 for Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
Figure 3 for Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
Figure 4 for Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics
Viaarxiv icon

The Actor-Advisor: Policy Gradient With Off-Policy Advice

Add code
Feb 07, 2019
Figure 1 for The Actor-Advisor: Policy Gradient With Off-Policy Advice
Figure 2 for The Actor-Advisor: Policy Gradient With Off-Policy Advice
Figure 3 for The Actor-Advisor: Policy Gradient With Off-Policy Advice
Figure 4 for The Actor-Advisor: Policy Gradient With Off-Policy Advice
Viaarxiv icon

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

Add code
Sep 20, 2018
Figure 1 for Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Figure 2 for Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Figure 3 for Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Figure 4 for Dynamic Weights in Multi-Objective Deep Reinforcement Learning
Viaarxiv icon

Directed Policy Gradient for Safe Reinforcement Learning with Human Advice

Add code
Aug 13, 2018
Figure 1 for Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Figure 2 for Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Figure 3 for Directed Policy Gradient for Safe Reinforcement Learning with Human Advice
Viaarxiv icon

Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets

Add code
Sep 12, 2017
Figure 1 for Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Figure 2 for Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Figure 3 for Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Figure 4 for Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets
Viaarxiv icon