TAMER: Training an Agent Manually via Evaluative Reinforcement

By W. B. Knox, Peter Stone. 2008

204 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Control and Systems Engineering, LLM Agents & Tool Use, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Control and Systems Engineering

In LLM Agents & Tool Use

In Reinforcement Learning

Citations in the corpus

Augmented Language Models: a Survey (2023, background): “Besides learning to use external tools, RLHF has also proven useful for a wide range of language generation tasks, from summarization (Ziegler et al., 2019; Wu et al., 2021; Stiennon et al., 2020) to training more helpful, harmless, and accurate assistants (Glaese et al., 2022; Cohen et al., 2022; O”
Training Diffusion Models with Reinforcement Learning (2023, unknown): “Additional experiments studying zero-shot generlization and reward overoptimization are provided in Appendix E.1 and E.2, respectively.”
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (2023, methodology): “Attempting to discretize this form of feedback using a Likert scale (a range of discrete ratings; e.g., very bad, bad, ok, good, very good) simplifies the process of feedback collection [Knox and Stone, 2008, MacGlashan et al., 2017, Arumugam et al., 2019].”
Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards (2017, unknown): “is dynamic and inconsistent [24], [25].”
DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback (2018, background): “TAMER [9] is a current standard framework in human-in-the-loop RL, where the agent predicts human feedback and takes the action that is most likely to result in good feedback.”
A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development (2023, background): “, table cleaning or clothes folding) of which goals are complex and poorly-defined, it is difficult to construct a precise reward function to evaluate whether the task is well finished with limited sensor information [84].”
Unity: A General Platform for Intelligent Agents (2018, background): “…frameworks have been studied in the literature (Zhang et al., 2019) such as learning to imitate expert trajectories (Ho and Ermon, 2016), humans providing evaluative feedback to the agent (Knox and Stone, 2008), or humans manipulating the agent’s observed states and actions (Abel et al., 2016).”
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons (2023, methodology): “…models etc. (Novoseller et al., 2019; Sadigh et al., 2017; Christiano et al., 2017b; Kupcsik et al., 2018; Jain et al., 2013; Wirth et al., 2017; Knox and Stone, 2008; MacGlashan et al., 2017; Christiano et al., 2017a; Warnell et al., 2018; Brown et al., 2019; Shin et al., 2023; Ziegler et al.,…”
Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning (2020, background): “…are demonstrations (e.g., Ng & Russell, 2000; Abbeel & Ng, 2004; Ziebart et al., 2008; Fu et al., 2018), positive and negative feedback (e.g., Thomaz et al., 2006; Knox & Stone, 2008; MacGlashan et al., 2017), and trajectory preferences (e.g., Akrour et al., 2012; Christiano et al., 2017).”
Policy Shaping: Integrating Human Feedback with Reinforcement Learning (2013, background): “This is the most common way human feedback has been applied to RL [1] [2] [3] [4] [5].”