Search Results for author:
Found 12 papers, 5 papers with code
Toward Optimal LLM Alignments Using Two-Player Games
We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents.
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model; one that simultaneously minimizes the maximum likelihood estimation of the loss and a reward penalty term.
Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions.
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences.
Can Large Language Models Play Games? A Case Study of A Self-Play Approach
Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge.
Measuring and Reducing LLM Hallucination without Gold-Standard Answers
FEWL leverages the answers from off-the-shelf LLMs that serve as a proxy of gold-standard answers.
Human-Instruction-Free LLM Self-Alignment with Limited Samples
The key idea is to first retrieve high-quality samples related to the target domain and use them as In-context Learning examples to generate more samples.
Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon ("reason for future").
Behavior Contrastive Learning for Unsupervised Skill Discovery
Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective.
Policy Learning Using Weak Supervision
Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).
Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
In this work, we introduce a new family of loss functions that we name as peer loss functions, which enables learning from noisy labels and does not require a priori specification of the noise rates.
Ranked #15 on
Learning with noisy labels
on CIFAR-100N
Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning
Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
