Tag: adversarial reinforcement learning
Browse our exclusive articles!
Enhancing LLM Tool Use via Automated Feedback Environments
Discover how automated environments and feedback-driven training improve large language models' tool use and task execution precision.
How Children and Adults Learn Causality via Empowerment
Explore how children and adults use empowerment, controllability, and variability to build causal models and enhance learning.
RL-PLUS: Enhancing LLMs in Reinforcement Learning
Discover RL-PLUS, a hybrid-policy optimization method that overcomes capability boundary collapse in LLMs, boosting reasoning and problem-solving skills.
Enhancing LLM Reasoning with Reinforcement Learning in Pre-train Space
Discover how PreRL and Dual Space RL improve large language model reasoning by optimizing marginal distributions and pruning errors effectively.
Soft Q(λ): Multi-Step Off-Policy Entropy RL Method
Discover Soft Q(λ), a multi-step off-policy method enhancing entropy-regularised reinforcement learning with eligibility traces for better learning efficie...