REVIEW 4 cited by
B-Pref: Benchmarking Preference-Based Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a teacher's preferences without pre-defined rewards, thus overcoming concerns associated with reward engineering. However, it is difficult to quantify the progress in preference-based RL due to the lack of a commonly adopted benchmark. In this paper, we introduce B-Pref: a benchmark specially designed for preference-based RL. A key challenge with such a benchmark is providing the ability to evaluate candidate algorithms quickly, which makes relying on real human input for evaluation prohibitive. At the same time, simulating human input as giving perfect preferences for the ground truth reward function is unrealistic. B-Pref alleviates this by simulating teachers with a wide array of irrationalities, and proposes metrics not solely for performance but also for robustness to these potential irrationalities. We showcase the utility of B-Pref by using it to analyze algorithmic design choices, such as selecting informative queries, for state-of-the-art preference-based RL algorithms. We hope that B-Pref can serve as a common starting point to study preference-based RL more systematically. Source code is available at https://github.com/rll-research/B-Pref.
Forward citations
Cited by 4 Pith papers
-
Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models
DROPJ trains a world-model-based MPC agent from one-shot human preferences plus safety justifications, cutting training cost and improving deployment safety in car-racing simulations.
-
Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
Noisy-comparison random search reaches ε-stationarity in O(k/(p²ε²)) comparisons for smooth nonconvex objectives with k-dimensional active subspace.
-
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
CLARIFY uses contrastive learning on preference data to embed trajectories, then rejection-samples queries that humans can distinguish clearly, improving offline preference-based RL.
-
Residual Reward Models for Preference-based Reinforcement Learning
Combining a hand-designed or learned prior reward with a preference-trained residual improves sample efficiency and final performance in preference-based reinforcement learning.
Discussion (0). Sign in to comment.