Few-shot preference learning for human-in-the-loop rl
DJ Hejna III, D Sadigh - Conference on Robot Learning, 2023 - proceedings.mlr.press
While reinforcement learning (RL) has become a more popular approach for robotics,
designing sufficiently informative reward functions for complex tasks has proven to be …
designing sufficiently informative reward functions for complex tasks has proven to be …
Inverse preference learning: Preference-based rl without a reward function
Reward functions are difficult to design and often hard to align with human intent. Preference-
based Reinforcement Learning (RL) algorithms address these problems by learning reward …
based Reinforcement Learning (RL) algorithms address these problems by learning reward …
Learning zero-shot cooperation with humans, assuming humans are biased
There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an
agent that can cooperate with humans in a zero-shot fashion without using any human data …
agent that can cooperate with humans in a zero-shot fashion without using any human data …
Rap: Risk-aware prediction for robust planning
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-
aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under …
aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under …
A ranking game for imitation learning
We propose a new framework for imitation learning--treating imitation as a two-player
ranking-based game between a policy and a reward. In this game, the reward agent learns …
ranking-based game between a policy and a reward. In this game, the reward agent learns …
Self-adapting simulated artificial societies
B Gower-Winter - 2023 - open.uct.ac.za
Abstract Agent-Based Models (ABM) are computational models that utilize autonomous
agents to interact and adapt to the environments in which they occupy. They are used in …
agents to interact and adapt to the environments in which they occupy. They are used in …
[图书][B] Design of Intuitive and Risk-Perception-Aware Robotic Navigation Algorithms
A Suresh - 2022 - search.proquest.com
As robots become more integrated into society, their reasoning and actions will invariably be
evaluated by human decision makers. Thus, robots need to perceive, act, and reason like …
evaluated by human decision makers. Thus, robots need to perceive, act, and reason like …