Topics
BayesianSoftware
Copyright© (2013) by Neural Information Processing SystemsPresented at the 27th Annual Conference on Neural Information Processing Systems (NIPS 2013), 5-10 December 2013, Lake Tahoe, Nevada.A long term goal of Interactive Reinforcement Learning is to incorporate non- expert human feedback to solve complex tasks. Some state-of -the-art methods have approached this problem by mapping human information to rewards and values and iterating over them to compute better control policies. In this paper we argue for an alternate, more effective characterization of human feedback: Policy Shaping. We introduce Advise, a Bayesian approach that attempts to maximize the information gained from human feedback by utilizing it as direct policy label...
Interactive reinforcement learning can effectively facilitate the agent training via human feedback....
Abstract — In order to be useful in real-world situations, it is critical to allow non-technical use...
This paper describes a new information-theoretic policy evaluation technique for reinforcement learn...
A long term goal of Interactive Reinforcement Learning is to incorporate non-expert human feedback t...
For agents and robots to become more useful, they must be able to quickly learn from non-technical u...
The field of Reinforcement Learning is concerned with teaching agents to take optimal decisions t...
A prevalent approach for learning a control policy in the model-free domain is by engaging Reinforce...
Reinforcement Learning agents can be supported by feedback from human teachers in the learning loop ...
University of Technology Sydney. Faculty of Engineering and Information Technology.A promising metho...
Reinforcement learning offers a general framework to explain reward related learning in artificial a...
This paper makes a first step toward the integration of two subfields of machine learning, namely pr...
Deep Reinforcement Learning enables us to control increasingly complex and high-dimensional problems...
Reinforcement learning from human feedback (RLHF) has dramatically improved the real-world performan...
The current reward learning from human preferences could be used to resolve complex reinforcement le...
This paper makes a first step toward the integration of two subfields of machine learning, namely pr...
Interactive reinforcement learning can effectively facilitate the agent training via human feedback....
Abstract — In order to be useful in real-world situations, it is critical to allow non-technical use...
This paper describes a new information-theoretic policy evaluation technique for reinforcement learn...
A long term goal of Interactive Reinforcement Learning is to incorporate non-expert human feedback t...
For agents and robots to become more useful, they must be able to quickly learn from non-technical u...
The field of Reinforcement Learning is concerned with teaching agents to take optimal decisions t...
A prevalent approach for learning a control policy in the model-free domain is by engaging Reinforce...
Reinforcement Learning agents can be supported by feedback from human teachers in the learning loop ...
University of Technology Sydney. Faculty of Engineering and Information Technology.A promising metho...
Reinforcement learning offers a general framework to explain reward related learning in artificial a...
This paper makes a first step toward the integration of two subfields of machine learning, namely pr...
Deep Reinforcement Learning enables us to control increasingly complex and high-dimensional problems...
Reinforcement learning from human feedback (RLHF) has dramatically improved the real-world performan...
The current reward learning from human preferences could be used to resolve complex reinforcement le...
This paper makes a first step toward the integration of two subfields of machine learning, namely pr...
Interactive reinforcement learning can effectively facilitate the agent training via human feedback....
Abstract — In order to be useful in real-world situations, it is critical to allow non-technical use...
This paper describes a new information-theoretic policy evaluation technique for reinforcement learn...
Add to ORKG