Learning to predict consequences as a method of knowledge transfer in reinforcement learning
E Chalmers, EB Contreras, B Robertson… - IEEE transactions on …, 2017 - ieeexplore.ieee.org
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
[PDF][PDF] Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning
E Chalmers, EB Contreras, B Robertson… - IEEE …, 2018 - people.uleth.ca
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning
E Chalmers, EB Contreras… - … on neural networks …, 2018 - pubmed.ncbi.nlm.nih.gov
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning.
E Chalmers, EB Contreras, B Robertson… - IEEE Transactions on …, 2017 - europepmc.org
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
[PDF][PDF] Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning
E Chalmers, EB Contreras, B Robertson, A Luczak… - researchgate.net
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
[PDF][PDF] Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning
E Chalmers, EB Contreras, B Robertson… - IEEE …, 2018 - people.uleth.ca
The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-
error learning. To be capable of efficient, long-term learning, RL agents should be able to …
error learning. To be capable of efficient, long-term learning, RL agents should be able to …