Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning

• URL: http://arxiv.org/abs/2405.02456v1
• Date: Fri, 3 May 2024 19:43:30 GMT
• Title: Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
• Authors: Sihan Zeng, Thinh T. Doan, Justin Romberg,
• Abstract summary: Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average performance of the policy across tasks subject to bounds on the performance in each task.
• Score: 13.908826484332282
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-task reinforcement learning (RL) aims to find a single policy that effectively solves multiple tasks at the same time. This paper presents a constrained formulation for multi-task RL where the goal is to maximize the average performance of the policy across tasks subject to bounds on the performance in each task. We consider solving this problem both in the centralized setting, where information for all tasks is accessible to a single server, and in the decentralized setting, where a network of agents, each given one task and observing local information, cooperate to find the solution of the globally constrained objective using local communication. We first propose a primal-dual algorithm that provably converges to the globally optimal solution of this constrained formulation under exact gradient evaluations. When the gradient is unknown, we further develop a sampled-based actor-critic algorithm that finds the optimal policy using online samples of state, action, and reward. Finally, we study the extension of the algorithm to the linear function approximation setting.

Related papers

• Offline Multi-task Transfer RL with Representational Penalization [26.114893629771736]
  We study the problem of representation transfer in offline Reinforcement Learning (RL) We propose an algorithm to compute pointwise uncertainty measures for the learnt representation.
  arXiv  Detail & Related papers  (2024-02-19T21:52:44Z)
• Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning [46.28771270378047]
  Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private reward function corresponding to different tasks, while sharing the same transition kernel of the environment. We learn a globally optimal policy that maximizes the sum of the discounted total rewards of all the agents in a decentralized manner.
  arXiv  Detail & Related papers  (2023-11-01T00:15:18Z)
• Provable Offline Preference-Based Reinforcement Learning [95.00042541409901]
  We investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback. We consider the general reward setting where the reward can be defined over the whole trajectory. We introduce a new single-policy concentrability coefficient, which can be upper bounded by the per-trajectory concentrability.
  arXiv  Detail & Related papers  (2023-05-24T07:11:26Z)
• Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning [139.53668999720605]
  We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2023-05-08T16:20:03Z)
• Robust Subtask Learning for Compositional Generalization [20.54144051436337]
  We focus on the problem of training subtask policies in a way that they can be used to perform any task. We aim to maximize the worst-case performance over all tasks as opposed to the average-case performance.
  arXiv  Detail & Related papers  (2023-02-06T18:19:25Z)
• Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization [8.836422771217084]
  Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences. We introduce a novel algorithm that uses Generalized Policy Improvement (GPI) to define principled, formally-derived prioritization schemes. We empirically show that our method outperforms state-of-the-art MORL algorithms in challenging multi-objective tasks.
  arXiv  Detail & Related papers  (2023-01-18T20:54:40Z)
• Exploration via Planning for Information about the Optimal Trajectory [67.33886176127578]
  We develop a method that allows us to plan for exploration while taking the task and the current knowledge into account. We demonstrate that our method learns strong policies with 2x fewer samples than strong exploration baselines.
  arXiv  Detail & Related papers  (2022-10-06T20:28:55Z)
• Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer [7.970144204429356]
  We introduce an SF-based extension of the Optimistic Linear Support algorithm to learn a set of policies whose SFs form a convex coverage set. We prove that policies in this set can be combined via generalized policy improvement to construct optimal behaviors for any new linearly-expressible tasks.
  arXiv  Detail & Related papers  (2022-06-22T19:00:08Z)
• Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning [83.66080019570461]
  We propose two environment-agnostic, algorithm-agnostic quantitative metrics for task difficulty. We show that these metrics have higher correlations with normalized task solvability scores than a variety of alternatives. These metrics can also be used for fast and compute-efficient optimizations of key design parameters.
  arXiv  Detail & Related papers  (2021-03-23T17:49:50Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)

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.