Equivalence between Policy Gradients and Soft Q-Learning
OpenAI published a research result establishing a formal equivalence between policy gradient methods and soft Q-learning, two major families of reinforcement learning algorithms. The work shows that under entropy regularization, these approaches are mathematically equivalent, unifying previously separate lines of RL research. This has implications for algorithm design, theoretical understanding, and the development of hybrid RL methods.
Related guides (2)
Related events (8)
Evolved Policy Gradients: OpenAI Meta-Learning via Loss Function Evolution
OpenAI released Evolved Policy Gradients (EPG), a meta-learning method that evolves the loss function used to train reinforcement learning agents rather than hand-designing it. The approach enables faster adaptation to novel tasks, with agents demonstrating generalization to test-time scenarios outside their training distribution, such as navigating to objects placed in new locations. EPG represents an experimental direction in automated algorithm discovery for RL.
Global Convergence Theory for Wasserstein Policy Gradient in Entropy-Regularized RL
This paper establishes the first global convergence theory for Wasserstein Policy Gradient (WPG), a continuous-control RL optimization method that uses optimal-transport geometry over action distributions. The authors show that the Bellman recursion structure of entropy-regularized RL induces a Polyak–Łojasiewicz (PL) geometry that substitutes for classical convexity, enabling global convergence analysis. Key technical contributions include a statewise KL representation of the soft Bellman residual, a Bellman resolvent identity linking value improvement to relative Fisher information, and a uniform log-Sobolev inequality for the evolving Gibbs policy family. The result yields geometric contraction up to discretization bias, providing theoretical grounding for WPG in continuous-action settings.
GraphPO: Graph-based Policy Optimization reduces redundancy in LLM reasoning RL
GraphPO is a new reinforcement learning framework that represents reasoning rollouts as directed acyclic graphs rather than independent chains or trees, merging semantically equivalent reasoning paths into equivalence classes to share suffixes and reduce redundant exploration. The approach assigns efficiency advantages to incoming edges and correctness advantages to outgoing edges, deriving process supervision from outcome rewards. Experiments on three LLMs across reasoning and agentic search benchmarks show consistent improvements over chain- and tree-based baselines under equal token or response budgets. The method also provides theoretical guarantees on reduced advantage-estimation variance.
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
OpenAI published research showing that evolution strategies (ES), a decades-old optimization technique, can match standard reinforcement learning performance on benchmarks like Atari and MuJoCo. The approach offers practical advantages over RL including easier parallelization and fewer hyperparameter sensitivities. This positions ES as a viable alternative training paradigm for policy optimization tasks.
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
OpenAI published a research paper on variance reduction techniques for policy gradient methods in reinforcement learning. The work introduces action-dependent factorized baselines as a way to reduce variance in policy gradient estimates without introducing bias. This is a foundational RL training methodology contribution relevant to improving sample efficiency in reinforcement learning.
OpenAI Releases Proximal Policy Optimization (PPO)
OpenAI introduced Proximal Policy Optimization (PPO), a new class of reinforcement learning algorithms that match or exceed state-of-the-art performance while being simpler to implement and tune. PPO was adopted as OpenAI's default RL algorithm due to its balance of ease of use and strong performance. The release marked a significant methodological contribution to the RL field that would go on to underpin many subsequent AI training pipelines.
Scaling Laws for Reward Model Overoptimization
OpenAI published research investigating how reward model overoptimization scales with policy and reward model size in RLHF pipelines. The work characterizes the relationship between KL divergence from the initial policy and gold-standard reward, finding predictable degradation patterns as optimization pressure increases. This provides empirical grounding for understanding Goodhart's Law dynamics in language model fine-tuning and has implications for designing safer, more robust RLHF training regimes.
DRPO: Smooth divergence regularization replaces hard masking in LLM RL training
A new arXiv preprint proposes Divergence Regularized Policy Optimization (DRPO), a method that replaces the hard trust-region mask used in DPPO with a smooth advantage-weighted quadratic regularizer on policy shift. The approach addresses a known weakness in PPO and GRPO where importance ratios poorly proxy distributional shift in long-tailed vocabularies, and in DPPO where gradient signals are discarded rather than corrected at trust-region boundaries. Experiments across model scales, architectures, and precision settings show improved stability and efficiency in LLM RL post-training.