REVIEW 6 cited by
Risk-Averse Offline 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
Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previously collected by safe policies. While previous work considers optimizing the average performance using offline data, we focus on optimizing a risk-averse criteria, namely the CVaR. In particular, we present the Offline Risk-Averse Actor-Critic (O-RAAC), a model-free RL algorithm that is able to learn risk-averse policies in a fully offline setting. We show that O-RAAC learns policies with higher CVaR than risk-neutral approaches in different robot control tasks. Furthermore, considering risk-averse criteria guarantees distributional robustness of the average performance with respect to particular distribution shifts. We demonstrate empirically that in the presence of natural distribution-shifts, O-RAAC learns policies with good average performance.
Forward citations
Cited by 6 Pith papers
-
Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
FAN achieves state-of-the-art offline RL performance on robotic tasks by anchoring flow policies and using single-sample noise-conditioned Q-learning, with proven convergence and reduced runtimes.
-
RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
RS-Diffuser integrates diffusion planners, quantile regression critics, and CVaR-style guidance to produce risk-averse to risk-seeking behaviors from one model in offline RL.
-
Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
FAN simplifies expressive flow policies and distributional critics in offline RL via single-iteration behavior regularization and single-sample noise conditioning to claim SOTA performance with lower training and infe...
-
Distributional Inverse Reinforcement Learning
DistIRL recovers reward distributions and risk-aware policies from offline demonstrations by minimizing first-order stochastic dominance violations between agent and expert returns.
-
Distributional Inverse Reinforcement Learning
A distributional offline IRL method minimizes first-order stochastic dominance violations to recover reward distributions and distribution-aware policies, with O(ε^{-2}) convergence and reported SOTA results on synthe...
-
MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics
MASK schedules top-K agents via semantic gating and a global encoder to achieve risk-aware multi-robot coordination that matches unconstrained baselines under bandwidth caps.
Discussion (0). Sign in to comment.