ADR-BC: Adversarial Density Weighted Regression Behavior Cloning
- URL: http://arxiv.org/abs/2405.20351v1
- Date: Tue, 28 May 2024 06:59:16 GMT
- Title: ADR-BC: Adversarial Density Weighted Regression Behavior Cloning
- Authors: Ziqi Zhang, Zifeng Zhuang, Donglin Wang, Jingzehua Xu, Miao Liu, Shuai Zhang,
- Abstract summary: Imitation Learning (IL) methods first shape a reward or Q function and then use this shaped function within a reinforcement learning framework to optimize the empirical policy.
We propose ADR-BC, which aims to enhance behavior cloning through augmented density-based action support.
As a one-step behavior cloning framework, ADR-BC avoids the cumulative bias associated with multi-step RL frameworks.
- Score: 29.095342729527733
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.
We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset.
arXiv Detail & Related papers (2024-10-10T16:01:51Z) - Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning [12.112619241073158]
In offline reinforcement learning, the challenge of out-of-distribution is pronounced.
Existing methods often constrain the learned policy through policy regularization.
We propose Adaptive Advantage-guided Policy Regularization (A2PR)
arXiv Detail & Related papers (2024-05-30T10:20:55Z) - Anti-Exploration by Random Network Distillation [63.04360288089277]
We show that a naive choice of conditioning for the Random Network Distillation (RND) is not discriminative enough to be used as an uncertainty estimator.
We show that this limitation can be avoided with conditioning based on Feature-wise Linear Modulation (FiLM)
We evaluate it on the D4RL benchmark, showing that it is capable of achieving performance comparable to ensemble-based methods and outperforming ensemble-free approaches by a wide margin.
arXiv Detail & Related papers (2023-01-31T13:18:33Z) - STEEL: Singularity-aware Reinforcement Learning [14.424199399139804]
Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy.
We propose a new batch RL algorithm that allows for singularity for both state and action spaces.
By leveraging the idea of pessimism and under some technical conditions, we derive a first finite-sample regret guarantee for our proposed algorithm.
arXiv Detail & Related papers (2023-01-30T18:29:35Z) - Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time
Guarantees [56.848265937921354]
Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy.
Many algorithms for IRL have an inherently nested structure.
We develop a novel single-loop algorithm for IRL that does not compromise reward estimation accuracy.
arXiv Detail & Related papers (2022-10-04T17:13:45Z) - Where is the Grass Greener? Revisiting Generalized Policy Iteration for
Offline Reinforcement Learning [81.15016852963676]
We re-implement state-of-the-art baselines in the offline RL regime under a fair, unified, and highly factorized framework.
We show that when a given baseline outperforms its competing counterparts on one end of the spectrum, it never does on the other end.
arXiv Detail & Related papers (2021-07-03T11:00:56Z) - Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate
Estimation [29.27760413892272]
Post-click conversion, as a strong signal indicating the user preference, is salutary for building recommender systems.
Currently, most existing methods utilize counterfactual learning to debias recommender systems.
We propose a novel double learning approach for the MRDR estimator, which can convert the error imputation into the general CVR estimation.
arXiv Detail & Related papers (2021-05-28T06:59:49Z) - Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality [131.45028999325797]
We develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP.
DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize.
We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $epsilon$-accurate optimal policy.
arXiv Detail & Related papers (2021-02-23T18:56:13Z) - Provably Good Batch Reinforcement Learning Without Great Exploration [51.51462608429621]
Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks.
Recent algorithms have shown promise but can still be overly optimistic in their expected outcomes.
We show that a small modification to Bellman optimality and evaluation back-up to take a more conservative update can have much stronger guarantees.
arXiv Detail & Related papers (2020-07-16T09:25:54Z)
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.