Related papers: Offline Behavior Distillation
Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demonstrations have been collected. Existing offline-to-online learning methods…
Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action distributions, where multiple behaviours are represented in…
On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to…
We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…
We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…
Offline reinforcement learning (RL) struggles in environments with rich and noisy inputs, where the agent only has access to a fixed dataset without environment interactions. Past works have proposed common workarounds based on the…
Offline reinforcement learning (RL) enables agents to learn policies from fixed datasets, avoiding costly or unsafe environment interactions. However, its effectiveness is often limited by dataset sparsity and the lack of transition overlap…
Offline reinforcement learning restricts the learning process to rely only on logged-data without access to an environment. While this enables real-world applications, it also poses unique challenges. One important challenge is dealing with…
Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework,…
In preference-based reinforcement learning (PbRL), a reward function is learned from a type of human feedback called preference. To expedite preference collection, recent works have leveraged \emph{offline preferences}, which are…
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour. The second step has been widely studied in the…
Offline reinforcement learning (RL) aims to learn a policy from a static dataset without further interactions with the environment. Collecting sufficiently large datasets for offline RL is exhausting since this data collection requires…
Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…
In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the…
On-policy distillation is pivotal for transferring reasoning capabilities to capacity-constrained models, yet remains prone to instability and negative transfer. We show that on-policy distillation can be interpreted, both theoretically and…
Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy…
Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…
Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn…