Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

• URL: http://arxiv.org/abs/2606.02194v1
• Date: Mon, 01 Jun 2026 12:49:14 GMT
• Title: Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
• Abstract summary: Reinforcement learning can be used to finetune policies further using additional experience.<n>In inverse reinforcement learning, a dense reward function is learned from expert demonstrations.<n>We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $geq 90%$ success rate on five out of six complex manipulation tasks.
• Score: 24.576576709809036
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for the typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy through using a specific reward formulation with theoretical guarantees. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $\geq 90\%$ success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.

Related papers

• RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization [65.23034604711489]
  We introduce RLoop, a self-improving framework for training large reasoning models.<n>RLoop transforms the standard training process into a virtuous cycle: it first uses RL to explore the solution space from a given policy, then filters the successful trajectories to create an expert dataset.<n>Our experiments show RLoops forgetting and substantially improves generalization, boosting average accuracy by 9% and pass@32 by over 15% compared to vanilla RL.
  arXiv  Detail & Related papers  (2025-11-06T11:27:16Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation [37.36913210031282]
  Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. We propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
  arXiv  Detail & Related papers  (2024-05-29T01:49:20Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency [7.806014635635933]
  We propose a method that uses primitive behaviours that have been previously learned to solve simple tasks. This guidance is not executed by a manually designed curriculum, but rather using a critic network to decide at each timestep whether or not to use the actions proposed. We demonstrate the agents can learn a successful policy faster when using our proposed method, both in terms of sample efficiency and computation time.
  arXiv  Detail & Related papers  (2023-10-03T06:49:57Z)
• Reward Uncertainty for Exploration in Preference-based Reinforcement Learning [88.34958680436552]
  We present an exploration method specifically for preference-based reinforcement learning algorithms. Our main idea is to design an intrinsic reward by measuring the novelty based on learned reward. Our experiments show that exploration bonus from uncertainty in learned reward improves both feedback- and sample-efficiency of preference-based RL algorithms.
  arXiv  Detail & Related papers  (2022-05-24T23:22:10Z)
• Jump-Start Reinforcement Learning [68.82380421479675]
  We present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks. We show via experiments that JSRL is able to significantly outperform existing imitation and reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2022-04-05T17:25:22Z)
• Robust Predictable Control [149.71263296079388]
  We show that our method achieves much tighter compression than prior methods, achieving up to 5x higher reward than a standard information bottleneck. We also demonstrate that our method learns policies that are more robust and generalize better to new tasks.
  arXiv  Detail & Related papers  (2021-09-07T17:29:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.