4arXiv cs.LG (Machine Learning)·
FORE: Fitted occupancy-ratio evaluation for offline RL without Bellman completeness
A new arXiv preprint introduces Fitted Occupancy-Ratio Evaluation (FORE), a fixed-point method for estimating discounted occupancy ratios in offline reinforcement learning and off-policy evaluation. FORE uses an adjoint Bellman recursion and projects onto a log-ratio class in KL divergence, requiring only realizability of the occupancy ratio rather than Bellman completeness or projected-operator stability. The authors establish finite-sample regret bounds and show convergence in KL up to approximation and statistical error, supporting value estimation via reward reweighting, occupancy-weighted fitted Q-evaluation, and doubly robust estimation. The result identifies occupancy-ratio realizability as a sufficient condition for offline policy evaluation, relaxing a standard assumption in the field.
Related guides (1)
Related events (8)
RL without TD Learning: Divide-and-Conquer Value Learning for Long-Horizon Off-Policy RL
A BAIR blog post introduces a divide-and-conquer paradigm for off-policy reinforcement learning that avoids temporal difference (TD) learning's error accumulation problem by reducing Bellman recursions logarithmically rather than linearly. The approach leverages the triangle inequality structure of goal-conditioned RL to define a transitive Bellman update rule, enabling value learning that scales to long-horizon tasks. The authors claim this is the first practical realization of divide-and-conquer value learning at scale in goal-conditioned RL settings, building on an idea traceable to Kaelbling (1993). The post frames this as a third paradigm alongside TD and Monte Carlo methods, addressing a key gap in scalable off-policy RL.
ACPO: Adaptive Clip Policy Optimization improves RLVR training for LLM reasoning
A new arXiv preprint provides theoretical analysis of Reinforcement Learning from Verifiable Rewards (RLVR) updates, identifying off-policy degree and gradient expectation as key factors governing update dynamics. The authors show that differences in gradient steps per rollout substantially affect importance sampling ratio distributions and which tokens dominate updates. Based on this analysis, they propose Adaptive Clip Policy Optimization (ACPO), which adjusts clipping boundaries per token group by empirical variance of importance sampling ratios, outperforming DAPO and CISPO baselines on 3B and 7B models across math, tabular QA, and logic benchmarks.
RELEX: Extrapolating LLM RLVR Training via Rank-1 Parameter Trajectories
This paper demonstrates that RLVR weight update trajectories are extremely low-rank and near-linearly predictable, with a rank-1 approximation capturing most downstream performance gains. The authors propose RELEX, a compute-efficient method that observes a short training window, estimates the rank-1 subspace, and extrapolates future checkpoints via linear regression—requiring no additional training. Evaluated on Qwen2.5-Math-1.5B, Qwen3-4B-Base, and Qwen3-8B-Base, RELEX matches or exceeds full RLVR performance using as few as 15% of training steps, and can extrapolate up to 10–20× beyond the observed prefix. The authors attribute the method's effectiveness to a denoising effect from rank-1 projection that discards stochastic optimization noise.
Putting RL back in RLHF: RLOO Implementation on Hugging Face
Hugging Face published a blog post introducing RLOO (REINFORCE Leave-One-Out), a reinforcement learning algorithm aimed at making the RL component of RLHF more practical and effective. The post discusses implementation details and motivations for revisiting pure RL-based fine-tuning approaches within the TRL library. This represents a technical contribution to the alignment and RLHF tooling ecosystem, offering an alternative to PPO-based RLHF pipelines.
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
DRIFT is a training framework that bridges online RL and offline SFT for multi-turn LLM optimization by exploiting the theoretical equivalence between KL-regularized RL and importance-weighted supervised learning. It decouples rollout generation from policy optimization: trajectories are sampled from a fixed reference policy offline, weighted by return-based importance scores, and used for weighted SFT. Empirically, DRIFT matches or exceeds multi-turn RL baselines while retaining the efficiency and simplicity of standard supervised fine-tuning. Code is publicly released.
Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
This paper investigates whether extrapolative weight averaging of RL-trained checkpoints can extend Pareto frontiers between competing objectives (correctness vs. computational efficiency) without additional training. Starting from a shared initialization, the authors train checkpoints under nested unit-test coverage regimes for competitive programming tasks, revealing a correctness-efficiency frontier where higher-coverage rewards reduce optimization failures but increase correctness failures. Extrapolation beyond trained endpoints produces complementary policies that, when ensembled, improve pass@250 on LCB/hard by 3.3% over the best single checkpoint at matched sample budget. Results hold across 7B and 32B model scales and three inference settings: pure reasoning, tool use, and agentic coding.
STARE: Token-level advantage reweighting to prevent entropy collapse in GRPO-style RL training
Researchers introduce STARE, a method addressing policy entropy collapse in GRPO-style reinforcement learning from verifiable rewards (RLVR) for LLM post-training. Through first-order gradient analysis, they identify a token-level credit assignment mismatch and propose selectively reweighting advantages for entropy-critical tokens using batch-internal surprisal quantiles plus a closed-loop entropy gate. Evaluated across 1.5B–32B models on short/long chain-of-thought and multi-turn tool use tasks, STARE outperforms DAPO and other baselines by 4–8% on AIME24/25 while sustaining stable training over thousands of steps.
HABC: Hierarchical Advantage Weighting for Online RL Fine-Tuning of Vision-Language-Action Policies
Researchers introduce Hierarchical Advantage-Weighted Behavior Cloning (HABC), a method for fine-tuning pretrained Vision-Language-Action (VLA) policies via online RL using only sparse binary episode outcomes. HABC trains separate critic heads for viability and efficiency objectives, combines them via a state-adaptive gate, and applies intervention-aware credit assignment to avoid incorrect supervision across human-intervention boundaries. On three contact-rich bimanual real-robot tasks, HABC improves success rates from SFT baselines of 36%, 44%, and 12% to 92%, 88%, and 38% respectively. The work addresses a fundamental credit assignment problem in robot learning from sparse outcome signals.