TRAM: Test-Time Risk Adaptation with Mixture of Agents
cs.LG
Submitted: 2024-08-16
Updated: 2026-11-06
Code: https://github.com/mike-gimelfarb/deep-successor-features-for-transfer
Terminology
Sources
- Risk-Averse Trust Region Optimization for Reward-Volatility Reduction
- Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
- RewardBench: Evaluating Reward Models for Language Modeling
- Situational Awareness by Risk-Conscious Skills
- Variance Reduction for Reinforcement Learning in Input-Driven Environments
- Controlled Decoding from Language Models
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning
- Learning to be Safe: Deep RL with a Safety Critic
- SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis