Related papers: Constrained Policy Optimization with Explicit Beha…
Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…
This paper presents a constrained policy gradient algorithm. We introduce constraints for safe learning with the following steps. First, learning is slowed down (lazy learning) so that the episodic policy change can be computed with the…
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…
In offline reinforcement learning (RL), addressing the out-of-distribution (OOD) action issue has been a focus, but we argue that there exists an OOD state issue that also impairs performance yet has been underexplored. Such an issue…
Offline reinforcement learning (RL) can fit strong value functions from fixed datasets, yet reliable deployment still hinges on the action selection interface used to query them. When the dataset induces a branched or multimodal action…
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a…
Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly…
Safety in reinforcement learning (RL) is typically enforced through objective shaping while keeping environment dynamics stationary with respect to observable state-action pairs. Under delayed harm, this can lead to replay: after a washout…
Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning…
Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…
Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…
Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation. In this paper, we propose an implicit actor-critic (iAC)…
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…
Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safety and performance…
Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to…
When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although…
In offline reinforcement learning, a policy needs to be learned from a single pre-collected dataset. Typically, policies are thus regularized during training to behave similarly to the data generating policy, by adding a penalty based on a…
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using the proximity of one single old policy as the normal trust…
Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…
Hybrid RL is the setting where an RL agent has access to both offline data and online data by interacting with the real-world environment. In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method…