Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only

Improving the performance of pre-trained policies through online reinforcement learning (RL) is a critical yet challenging topic. Existing online RL fine-tuning methods require continued training with offline pretrained Q-functions for stability and performance. However, these offline pretrained Q-functions commonly underestimate state-action pairs beyond the offline dataset due to the conservatism in most offline RL methods, which hinders further exploration when transitioning from the offline to the online setting. Additionally, this requirement limits their applicability in scenarios where only pre-trained policies are available but pre-trained Q-functions are absent, such as in imitation learning (IL) pre-training. To address these challenges, we propose a method for efficient online RL fine-tuning using solely the offline pre-trained policy, eliminating reliance on pre-trained Q-functions. We introduce PORL (Policy-Only Reinforcement Learning Fine-Tuning), which rapidly initializes the Q-function from scratch during the online phase to avoid detrimental pessimism. Our method not only achieves competitive performance with advanced offline-to-online RL algorithms and online RL approaches that leverage data or policies prior, but also pioneers a new path for directly fine-tuning behavior cloning (BC) policies.

VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL

Diffusion models have emerged as powerful generative tools across various domains, yet tailoring pre-trained models to exhibit specific desirable properties remains challenging. While reinforcement learning (RL) offers a promising solution,current methods struggle to simultaneously achieve stable, efficient fine-tuning and support non-differentiable rewards. Furthermore, their reliance on sparse rewards provides inadequate supervision during intermediate steps, often resulting in suboptimal generation quality. To address these limitations, dense and differentiable signals are required throughout the diffusion process. Hence, we propose VAlue-based Reinforced Diffusion (VARD): a novel approach that first learns a value function predicting expection of rewards from intermediate states, and subsequently uses this value function with KL regularization to provide dense supervision throughout the generation process. Our method maintains proximity to the pretrained model while enabling effective and stable training via backpropagation. Experimental results demonstrate that our approach facilitates better trajectory guidance, improves training efficiency and extends the applicability of RL to diffusion models optimized for complex, non-differentiable reward functions.

ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning

Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other hand, offline Reinforcement Learning (RL) excels at learning robust policy models from mixed-quality data. In this paper, we introduce Reinforced robot GPT (ReinboT), a novel end-to-end VLA model that integrates the RL principle of maximizing cumulative reward. ReinboT achieves a deeper understanding of the data quality distribution by predicting dense returns that capture the nuances of manipulation tasks. The dense return prediction capability enables the robot to generate more robust decision-making actions, oriented towards maximizing future benefits. Extensive experiments show that ReinboT achieves state-of-the-art performance on the CALVIN mixed-quality dataset and exhibits superior few-shot learning and out-of-distribution generalization capabilities in real-world tasks.

TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control

Complex high-dimensional spaces with high Degree-of-Freedom and complicated action spaces, such as humanoid robots equipped with dexterous hands, pose significant challenges for reinforcement learning (RL) algorithms, which need to wisely balance exploration and exploitation under limited sample budgets. In general, feasible regions for accomplishing tasks within complex high-dimensional spaces are exceedingly narrow. For instance, in the context of humanoid robot motion control, the vast majority of space corresponds to falling, while only a minuscule fraction corresponds to standing upright, which is conducive to the completion of downstream tasks. Once the robot explores into a potentially task-relevant region, it should place greater emphasis on the data within that region. Building on this insight, we propose the $\textbf{S}$elf-$\textbf{I}$mitative $\textbf{R}$einforcement $\textbf{L}$earning ($\textbf{SIRL}$) framework, where the RL algorithm also imitates potentially task-relevant trajectories. Specifically, trajectory return is utilized to determine its relevance to the task and an additional behavior cloning is adopted whose weight is dynamically adjusted based on the trajectory return. As a result, our proposed algorithm achieves 120% performance improvement on the challenging HumanoidBench with 5% extra computation overhead. With further visualization, we find the significant performance gain does lead to meaningful behavior improvement that several tasks are solved successfully.

Q-WSL:Leveraging Dynamic Programming for Weighted Supervised Learning in Goal-conditioned RL

A novel class of advanced algorithms, termed Goal-Conditioned Weighted Supervised Learning (GCWSL), has recently emerged to tackle the challenges posed by sparse rewards in goal-conditioned reinforcement learning (RL). GCWSL consistently delivers strong performance across a diverse set of goal-reaching tasks due to its simplicity, effectiveness, and stability. However, GCWSL methods lack a crucial capability known as trajectory stitching, which is essential for learning optimal policies when faced with unseen skills during testing. This limitation becomes particularly pronounced when the replay buffer is predominantly filled with sub-optimal trajectories. In contrast, traditional TD-based RL methods, such as Q-learning, which utilize Dynamic Programming, do not face this issue but often experience instability due to the inherent difficulties in value function approximation. In this paper, we propose Q-learning Weighted Supervised Learning (Q-WSL), a novel framework designed to overcome the limitations of GCWSL by incorporating the strengths of Dynamic Programming found in Q-learning. Q-WSL leverages Dynamic Programming results to output the optimal action of (state, goal) pairs across different trajectories within the replay buffer. This approach synergizes the strengths of both Q-learning and GCWSL, effectively mitigating their respective weaknesses and enhancing overall performance. Empirical evaluations on challenging goal-reaching tasks demonstrate that Q-WSL surpasses other goal-conditioned approaches in terms of both performance and sample efficiency. Additionally, Q-WSL exhibits notable robustness in environments characterized by binary reward structures and environmental stochasticity.

ADR-BC: Adversarial Density Weighted Regression Behavior Cloning

Typically, traditional Imitation Learning (IL) methods first shape a reward or Q function and then use this shaped function within a reinforcement learning (RL) framework to optimize the empirical policy. However, if the shaped reward/Q function does not adequately represent the ground truth reward/Q function, updating the policy within a multi-step RL framework may result in cumulative bias, further impacting policy learning. Although utilizing behavior cloning (BC) to learn a policy by directly mimicking a few demonstrations in a single-step updating manner can avoid cumulative bias, BC tends to greedily imitate demonstrated actions, limiting its capacity to generalize to unseen state action pairs. To address these challenges, we propose ADR-BC, which aims to enhance behavior cloning through augmented density-based action support, optimizing the policy with this augmented support. Specifically, the objective of ADR-BC shares the similar physical meanings that matching expert distribution while diverging the sub-optimal distribution. Therefore, ADR-BC can achieve more robust expert distribution matching. Meanwhile, as a one-step behavior cloning framework, ADR-BC avoids the cumulative bias associated with multi-step RL frameworks. To validate the performance of ADR-BC, we conduct extensive experiments. Specifically, ADR-BC showcases a 10.5% improvement over the previous state-of-the-art (SOTA) generalized IL baseline, CEIL, across all tasks in the Gym-Mujoco domain. Additionally, it achieves an 89.5% improvement over Implicit Q Learning (IQL) using real rewards across all tasks in the Adroit and Kitchen domains. On the other hand, we conduct extensive ablations to further demonstrate the effectiveness of ADR-BC.

DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation

In this paper, we propose a novel approach called DIffusion-guided DIversity (DIDI) for offline behavioral generation. The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data. We achieve this by leveraging diffusion probabilistic models as priors to guide the learning process and regularize the policy. By optimizing a joint objective that incorporates diversity and diffusion-guided regularization, we encourage the emergence of diverse behaviors while maintaining the similarity to the offline data. Experimental results in four decision-making domains (Push, Kitchen, Humanoid, and D4RL tasks) show that DIDI is effective in discovering diverse and discriminative skills. We also introduce skill stitching and skill interpolation, which highlight the generalist nature of the learned skill space. Further, by incorporating an extrinsic reward function, DIDI enables reward-guided behavior generation, facilitating the learning of diverse and optimal behaviors from sub-optimal data.

Reinformer: Max-Return Sequence Modeling for offline RL

As a data-driven paradigm, offline reinforcement learning (RL) has been formulated as sequence modeling that conditions on the hindsight information including returns, goal or future trajectory. Although promising, this supervised paradigm overlooks the core objective of RL that maximizes the return. This overlook directly leads to the lack of trajectory stitching capability that affects the sequence model learning from sub-optimal data. In this work, we introduce the concept of max-return sequence modeling which integrates the goal of maximizing returns into existing sequence models. We propose Reinforced Transformer (Reinformer), indicating the sequence model is reinforced by the RL objective. Reinformer additionally incorporates the objective of maximizing returns in the training phase, aiming to predict the maximum future return within the distribution. During inference, this in-distribution maximum return will guide the selection of optimal actions. Empirically, Reinformer is competitive with classical RL methods on the D4RL benchmark and outperforms state-of-the-art sequence model particularly in trajectory stitching ability. Code is public at \url{https://github.com/Dragon-Zhuang/Reinformer}.

Context-Former: Stitching via Latent Conditioned Sequence Modeling

Offline reinforcement learning (RL) algorithms can improve the decision making via stitching sub-optimal trajectories to obtain more optimal ones. This capability is a crucial factor in enabling RL to learn policies that are superior to the behavioral policy. On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance. In order to endow stitching capability to DT, we abstract trajectory stitching as expert matching and introduce our approach, ContextFormer, which integrates contextual information-based imitation learning (IL) and sequence modeling to stitch sub-optimal trajectory fragments by emulating the representations of a limited number of expert trajectories. To validate our claim, we conduct experiments from two perspectives: 1) We conduct extensive experiments on D4RL benchmarks under the settings of IL, and experimental results demonstrate ContextFormer can achieve competitive performance in multi-IL settings. 2) More importantly, we conduct a comparison of ContextFormer with diverse competitive DT variants using identical training datasets. The experimental results unveiled ContextFormer's superiority, as it outperformed all other variants, showcasing its remarkable performance.

Adaptive Proximal Policy Optimization with Upper Confidence Bound

Trust Region Policy Optimization (TRPO) attractively optimizes the policy while constraining the update of the new policy within a trust region, ensuring the stability and monotonic optimization. Building on the theoretical guarantees of trust region optimization, Proximal Policy Optimization (PPO) successfully enhances the algorithm's sample efficiency and reduces deployment complexity by confining the update of the new and old policies within a surrogate trust region. However, this approach is limited by the fixed setting of surrogate trust region and is not sufficiently adaptive, because there is no theoretical proof that the optimal clipping bound remains consistent throughout the entire training process, truncating the ratio of the new and old policies within surrogate trust region can ensure that the algorithm achieves its best performance, therefore, exploring and researching a dynamic clip bound for improving PPO's performance can be quite beneficial. To design an adaptive clipped trust region and explore the dynamic clip bound's impact on the performance of PPO, we introduce an adaptive PPO-CLIP (Adaptive-PPO) method that dynamically explores and exploits the clip bound using a bandit during the online training process. Furthermore, ample experiments will initially demonstrate that our Adaptive-PPO exhibits sample efficiency and performance compared to PPO-CLIP.