Papers

Field

Top tools here

Open problems in Learning verifiable rewards

Poor credit assignment in diffusion model RL1 paper raises it · 1 addresses it
Limits efficiency and stability when fine-tuning diffusion models with black-box rewards.
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Modelsraises · addresses
Vanishing group-relative reward signals1 paper raises it · 1 addresses it
All rollouts receiving the same reward lose useful trajectory-level information for learning.
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresightraises · addresses
Memory inefficiency in LLM RL post-training1 paper raises it · 1 addresses it
High memory demands prevent scaling RL to larger models or longer training runs.
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketchesraises · addresses
Sparse terminal rewards degrade value tracking1 paper raises it · 1 addresses it
Standard critics fail to model value evolution along trajectories, harming credit assignment.
- TPPO: Tracking-Value PPO For Language Model Reasoningraises · addresses
Reward hacking in rubric-based RL1 paper raises it · 1 addresses it
Additive reward aggregation allows policies to exploit criteria compensation, reducing task appropriateness.
- Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubricsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable329 papers53 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers36 this week
optimal regret · near optimal · bandits217 papers33 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers15 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers14 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGOct 3
LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games
Chengyu Luan, Bo Xin, Songyan Guo, Yuxiang Zuo, Ahmed Yazdan +2
Large language models can intervene in reinforcement learning through both reward design and action selection, yet aggregate performance offers an incomplete account of what these interventions actually do. Similar returns can conceal different learning mechanisms, while plausible rewards can induce undesirable behavior. We introduce LocusRL, a diagnostic framework that connects controlled reward-policy comparisons with audits of reward judgments, signal delivery, optimization objectives, and executed actions. The framework traces performance differences to testable explanations and checks targeted corrections through executable rules and counterfactual replay. Across two evaluation batches covering ten Connect Four training seeds, we uncover seed-dependent reversals in intervention effects and show how tracing actual updates changes their interpretation: historical Qwen training operates through reward-weighted teacher-action likelihood. A separate matched three-seed reward-direction experiment distinguishes sensitivity to a learning signal from its usefulness. With terminal rewards held fixed, a sign-reversed dense oracle yields a 2.8% aggregate win rate, compared with 57.2%…
PDF arXiv
arXiv cs.AIOct 3
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
Santhosh GS, Ananya Ravi, Devika Jay, Abhishek Sarkar, Perepu Satheesh Kumar +3
The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objective specifications and robustness under real-world environmental drift. However, to protect intellectual property, the RL agent may be delivered for evaluation as opaque executable or remote API, which makes traditional evaluation techniques based on the internals of the policies infeasible. To address this gap, CORE-RL: Confidence-Oriented Reliability Evaluation of black box RL policy is proposed in this paper. The CORE-RL pipeline introduces a Unified Reliability Metric that formally integrates early task termination and safety constraint violations, preventing unsafe policies from masking failures through premature episode halts. By subjecting the policy to a noise certification envelope of perceptual noise, actuation noise and change in environment dynamics, the pipeline computes the finite-sample Clopper-Pearson bounds on unified reliability metric and Hoeffdings' lower bound on reward and safety cost. The pipeline then defines safe operational design domain to report high-confidence certificates for…
PDF arXiv
arXiv cs.LGOct 3
A Bird's-Eye View of Iterative Reward Design
Logan Mondal Bhamidipaty, Lauren Robson, Linda Petrini, Shengrui Lyu, Kamal Ndousse
Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and iteratively improve reward code using policy feedback. However, these methods are often hard to compare because they differ in implementation details, feedback assumptions, and evaluation environments. To address this, we introduce a Benchmark for Iterative Reward Design (BIRD) that expresses existing methods in a unified configuration and evaluation space. This lets us compare algorithms directly, ablate individual design choices, and prototype new components under matched feedback conditions and policy-training budgets. Across MuJoCo, Meta-World, Assistax, and HumanoidBench, we identify a small set of simple design choices that consistently improve performance. Combining these choices yields significantly better performance than the evaluated methods from prior work. Our results highlight the strength of simple baselines and motivate further study of when additional algorithmic complexity improves iterative reward design. Code is available at https://github.com/safety-research/bird.
PDF arXiv
arXiv cs.LGOct 3
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng, Xuying Ning, Yanjun Zhao +4
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, group-based RLVR methods, such as GRPO, assign a uniform advantage to all tokens within rollouts of the same outcome. While existing works refine credit assignment of GRPO based on local signals such as token locations or entropy, they often fail to capture the global semantic novelty of a reasoning behavior relative to the current policy. In this work, we propose a hierarchical credit assignment approach for group-based RLVR methods, called HarA, which identifies and encourages semantically novel reasoning behaviors during RLVR. HarA represents each sampled rollout as a distribution over the hidden states and locations of tokens, and computes the Fused Gromov-Wasserstein (FGW) barycenters of all rollouts with the same outcome, capturing the internal reasoning patterns in the latent space under the current policy. The semantic novelty of a reasoning element can then be measured by its contribution to the FGW distance between the current rollout and the barycenter. While solving the FGW formulation is…
PDF arXiv
arXiv math.OCOct 3
Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems
Qi Feng, Gu Wang
We develop an amortized, grid-free implementation of continuous Langevin dynamics based policy-value iteration for entropy-regularized, infinite-horizon relaxed stochastic control problems. The improvement rate of the exact iteration is a discounted aggregate of relative Fisher information between the policy and the Gibbs law of its Hamiltonian. The associated score residual is the velocity with which the control's Langevin dynamics transport its law. We project this velocity onto a conditional sampler shared across states, instead of one Langevin dynamics per state, and the value dynamics onto a parametric critic, estimating both projections at sampled states to obtain coupled actor--critic flows. The score loss measures the actor's agreement with the current critic, while the policy-evaluation residual measures the critic's agreement with the actor. We also derive gradient and Hessian residuals, including a Feynman--Kac representation for the gradient equation, to control errors not detected by the projected value iteration. An exact decomposition of the HJB residual combines these errors into a policy-suboptimality bound under verification and logarithmic Sobolev assumptions.…
PDF arXiv
arXiv cs.NEOct 3
Adaptive Operator Selection in Bilevel Large Neighborhood Search for Electric Autonomous Dial-a-Ride Problem under Uncertainty
Ishara Hewa Pathiranange, Aneta Neumann
The electric autonomous dial-a-ride problem (EADARP) extends the classical dial-a-ride problem by incorporating battery and charging constraints for electric vehicles. In practice, travel-time uncertainty can cause violations of time-window constraints. Large neighborhood search is effective for solving the EADARP, but its performance can depend on the choice of insertion operator during the repair phase. This paper investigates insertion-operator selection within a bilevel large neighborhood search framework for deterministic and chance-constrained variants of the EADARP. In the chance-constrained variant, arc travel times are modeled as independent normally distributed random variables, and upper time-window constraints are enforced probabilistically. We consider six selection methods, namely fixed greedy insertion, fixed regret-based insertion, random selection, a deterministic state-based rule, performance-adaptive ALNS selection, and LLM-based state-aware selection. Experimental results show comparable performance on smaller instances, while differences become more evident on larger and more constrained instances. There is no single strategy that performs best across all…
PDF arXiv

Papers

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable329 papers53 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers36 this week
optimal regret · near optimal · bandits217 papers33 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers15 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers14 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.LGOct 3
LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games
Chengyu Luan, Bo Xin, Songyan Guo, Yuxiang Zuo, Ahmed Yazdan +2
Large language models can intervene in reinforcement learning through both reward design and action selection, yet aggregate performance offers an incomplete account of what these interventions actually do. Similar returns can conceal different learning mechanisms, while plausible rewards can induce undesirable behavior. We introduce LocusRL, a diagnostic framework that connects controlled reward-policy comparisons with audits of reward judgments, signal delivery, optimization objectives, and executed actions. The framework traces performance differences to testable explanations and checks targeted corrections through executable rules and counterfactual replay. Across two evaluation batches covering ten Connect Four training seeds, we uncover seed-dependent reversals in intervention effects and show how tracing actual updates changes their interpretation: historical Qwen training operates through reward-weighted teacher-action likelihood. A separate matched three-seed reward-direction experiment distinguishes sensitivity to a learning signal from its usefulness. With terminal rewards held fixed, a sign-reversed dense oracle yields a 2.8% aggregate win rate, compared with 57.2%…
PDF arXiv
arXiv cs.AIOct 3
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
Santhosh GS, Ananya Ravi, Devika Jay, Abhishek Sarkar, Perepu Satheesh Kumar +3
The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objective specifications and robustness under real-world environmental drift. However, to protect intellectual property, the RL agent may be delivered for evaluation as opaque executable or remote API, which makes traditional evaluation techniques based on the internals of the policies infeasible. To address this gap, CORE-RL: Confidence-Oriented Reliability Evaluation of black box RL policy is proposed in this paper. The CORE-RL pipeline introduces a Unified Reliability Metric that formally integrates early task termination and safety constraint violations, preventing unsafe policies from masking failures through premature episode halts. By subjecting the policy to a noise certification envelope of perceptual noise, actuation noise and change in environment dynamics, the pipeline computes the finite-sample Clopper-Pearson bounds on unified reliability metric and Hoeffdings' lower bound on reward and safety cost. The pipeline then defines safe operational design domain to report high-confidence certificates for…
PDF arXiv
arXiv cs.LGOct 3
A Bird's-Eye View of Iterative Reward Design
Logan Mondal Bhamidipaty, Lauren Robson, Linda Petrini, Shengrui Lyu, Kamal Ndousse
Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and iteratively improve reward code using policy feedback. However, these methods are often hard to compare because they differ in implementation details, feedback assumptions, and evaluation environments. To address this, we introduce a Benchmark for Iterative Reward Design (BIRD) that expresses existing methods in a unified configuration and evaluation space. This lets us compare algorithms directly, ablate individual design choices, and prototype new components under matched feedback conditions and policy-training budgets. Across MuJoCo, Meta-World, Assistax, and HumanoidBench, we identify a small set of simple design choices that consistently improve performance. Combining these choices yields significantly better performance than the evaluated methods from prior work. Our results highlight the strength of simple baselines and motivate further study of when additional algorithmic complexity improves iterative reward design. Code is available at https://github.com/safety-research/bird.
PDF arXiv
arXiv cs.LGOct 3
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng, Xuying Ning, Yanjun Zhao +4
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, group-based RLVR methods, such as GRPO, assign a uniform advantage to all tokens within rollouts of the same outcome. While existing works refine credit assignment of GRPO based on local signals such as token locations or entropy, they often fail to capture the global semantic novelty of a reasoning behavior relative to the current policy. In this work, we propose a hierarchical credit assignment approach for group-based RLVR methods, called HarA, which identifies and encourages semantically novel reasoning behaviors during RLVR. HarA represents each sampled rollout as a distribution over the hidden states and locations of tokens, and computes the Fused Gromov-Wasserstein (FGW) barycenters of all rollouts with the same outcome, capturing the internal reasoning patterns in the latent space under the current policy. The semantic novelty of a reasoning element can then be measured by its contribution to the FGW distance between the current rollout and the barycenter. While solving the FGW formulation is…
PDF arXiv
arXiv math.OCOct 3
Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems
Qi Feng, Gu Wang
We develop an amortized, grid-free implementation of continuous Langevin dynamics based policy-value iteration for entropy-regularized, infinite-horizon relaxed stochastic control problems. The improvement rate of the exact iteration is a discounted aggregate of relative Fisher information between the policy and the Gibbs law of its Hamiltonian. The associated score residual is the velocity with which the control's Langevin dynamics transport its law. We project this velocity onto a conditional sampler shared across states, instead of one Langevin dynamics per state, and the value dynamics onto a parametric critic, estimating both projections at sampled states to obtain coupled actor--critic flows. The score loss measures the actor's agreement with the current critic, while the policy-evaluation residual measures the critic's agreement with the actor. We also derive gradient and Hessian residuals, including a Feynman--Kac representation for the gradient equation, to control errors not detected by the projected value iteration. An exact decomposition of the HJB residual combines these errors into a policy-suboptimality bound under verification and logarithmic Sobolev assumptions.…
PDF arXiv
arXiv cs.NEOct 3
Adaptive Operator Selection in Bilevel Large Neighborhood Search for Electric Autonomous Dial-a-Ride Problem under Uncertainty
Ishara Hewa Pathiranange, Aneta Neumann
The electric autonomous dial-a-ride problem (EADARP) extends the classical dial-a-ride problem by incorporating battery and charging constraints for electric vehicles. In practice, travel-time uncertainty can cause violations of time-window constraints. Large neighborhood search is effective for solving the EADARP, but its performance can depend on the choice of insertion operator during the repair phase. This paper investigates insertion-operator selection within a bilevel large neighborhood search framework for deterministic and chance-constrained variants of the EADARP. In the chance-constrained variant, arc travel times are modeled as independent normally distributed random variables, and upper time-window constraints are enforced probabilistically. We consider six selection methods, namely fixed greedy insertion, fixed regret-based insertion, random selection, a deterministic state-based rule, performance-adaptive ALNS selection, and LLM-based state-aware selection. Experimental results show comparable performance on smaller instances, while differences become more evident on larger and more constrained instances. There is no single strategy that performs best across all…
PDF arXiv

Activity · 12 weeks

Open problems in Learning verifiable rewards

Poor credit assignment in diffusion model RL1 paper raises it · 1 addresses it
Limits efficiency and stability when fine-tuning diffusion models with black-box rewards.
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Modelsraises · addresses
Vanishing group-relative reward signals1 paper raises it · 1 addresses it
All rollouts receiving the same reward lose useful trajectory-level information for learning.
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresightraises · addresses
Memory inefficiency in LLM RL post-training1 paper raises it · 1 addresses it
High memory demands prevent scaling RL to larger models or longer training runs.
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketchesraises · addresses
Sparse terminal rewards degrade value tracking1 paper raises it · 1 addresses it
Standard critics fail to model value evolution along trajectories, harming credit assignment.
- TPPO: Tracking-Value PPO For Language Model Reasoningraises · addresses
Reward hacking in rubric-based RL1 paper raises it · 1 addresses it
Additive reward aggregation allows policies to exploit criteria compensation, reducing task appropriateness.
- Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubricsraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 1h ago

Learning verifiable rewards

Found by the topic model: learning verifiable rewards, optimal regret, offline reinforcement learning.

151papers this week−25.2% vs last week

All papers · 931 With code · 29

Newest Most relevant

878 papers this month