Pith. sign in

REVIEW 6 cited by

Constrained Policy Optimization via Bayesian World Models

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

arxiv 2201.09802 v4 pith:PSDKYXBU submitted 2022-01-24 cs.LG cs.AIcs.RO

classification cs.LGcs.AIcs.RO
keywords safetyworldapproachbayesianboundsconstrainedlambdamodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Improving sample-efficiency and safety are crucial challenges when deploying reinforcement learning in high-stakes real world applications. We propose LAMBDA, a novel model-based approach for policy optimization in safety critical tasks modeled via constrained Markov decision processes. Our approach utilizes Bayesian world models, and harnesses the resulting uncertainty to maximize optimistic upper bounds on the task objective, as well as pessimistic upper bounds on the safety constraints. We demonstrate LAMBDA's state of the art performance on the Safety-Gym benchmark suite in terms of sample efficiency and constraint violation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    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.

  2. Safe Planning and Policy Optimization via World Model Learning

    cs.AI 2025-06 conditional novelty 6.0 of 10

    SPOWL is a model-based safe RL method that uses a value-equivalent world model, a Lagrangian-trained safe policy, and adaptive planning thresholds to achieve low-cost, high-reward control on SafetyGymnasium tasks.

  3. Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation

    cs.LG 2024-12 conditional novelty 6.0 of 10

    The paper introduces Gradient-based Estimation (GBE), a Taylor-expansion method using analytic trajectory gradients, and the trust-region algorithm CGPO for safe RL with finite-horizon constraints.

  4. Q-learning-based Model-free Safety Filter

    cs.RO 2024-11 reject novelty 6.0 of 10

    A Q-learning safety filter with a time-dependent reward blocks unsafe actions from arbitrary task policies, but its theoretical guarantee is not valid as written.

  5. ACORN: Adaptive Contrastive Optimization for Safe and Robust Fine-Grained Robotic Manipulation

    cs.RO 2025-05 reject novelty 5.0 of 10

    ACORN adds contrastive learning with action-space perturbations to ACT imitation learning and reports improved safety metrics on one bimanual task, but the headline metric is undefined and results are inconsistent acr...

  6. Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A survey that organizes combinations of Bayesian inference and reinforcement learning, rates them on four properties, and raises ten open questions.

Pith tools