Natural Policy Gradient for Average Reward Non-Stationary RL

• URL: http://arxiv.org/abs/2504.16415v1
• Date: Wed, 23 Apr 2025 04:37:26 GMT
• Title: Natural Policy Gradient for Average Reward Non-Stationary RL
• Authors: Neharika Jali, Eshika Pathak, Pranay Sharma, Guannan Qu, Gauri Joshi,
• Abstract summary: We consider the problem of non-stationary reinforcement learning (RL) in the infinite-horizon average-reward setting.<n>Existing non-stationary RL algorithms focus on model-based and model-free value-based methods.<n>We propose and analyze the first model-free policy-based algorithm, Non-Stationary Natural Actor-Critic (NS-NAC)
• Score: 20.00962082306857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of non-stationary reinforcement learning (RL) in the infinite-horizon average-reward setting. We model it by a Markov Decision Process with time-varying rewards and transition probabilities, with a variation budget of $\Delta_T$. Existing non-stationary RL algorithms focus on model-based and model-free value-based methods. Policy-based methods despite their flexibility in practice are not theoretically well understood in non-stationary RL. We propose and analyze the first model-free policy-based algorithm, Non-Stationary Natural Actor-Critic (NS-NAC), a policy gradient method with a restart based exploration for change and a novel interpretation of learning rates as adapting factors. Further, we present a bandit-over-RL based parameter-free algorithm BORL-NS-NAC that does not require prior knowledge of the variation budget $\Delta_T$. We present a dynamic regret of $\tilde{\mathscr O}(|S|^{1/2}|A|^{1/2}\Delta_T^{1/6}T^{5/6})$ for both algorithms, where $T$ is the time horizon, and $|S|$, $|A|$ are the sizes of the state and action spaces. The regret analysis leverages a novel adaptation of the Lyapunov function analysis of NAC to dynamic environments and characterizes the effects of simultaneous updates in policy, value function estimate and changes in the environment.

Related papers

• Neural Policy Iteration for Stochastic Optimal Control: A Physics-Informed Approach [2.8988658640181826]
  We propose a physics-informed neural network policy iteration framework (PINN-PI)<n>At each iteration, a neural network is trained to approximate the value function by minimizing the residual of a linear PDE induced by a fixed policy.<n>We demonstrate the effectiveness of our method on several benchmark problems, including gradient cartpole, pendulum high-dimensional linear quadratic regulation (LQR) problems in up to 10D.
  arXiv  Detail & Related papers  (2025-08-03T11:02:25Z)
• Robust Offline Reinforcement Learning for Non-Markovian Decision Processes [48.9399496805422]
  We study the learning problem of robust offline non-Markovian RL. We introduce a novel dataset distillation and a lower confidence bound (LCB) design for robust values under different types of the uncertainty set. By further introducing a novel type-I concentrability coefficient tailored for offline low-rank non-Markovian decision processes, we prove that our algorithm can find an $epsilon$-optimal robust policy.
  arXiv  Detail & Related papers  (2024-11-12T03:22:56Z)
• Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs [63.47351876442425]
  We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback. We propose a novel algorithm that combines the benefits of two popular methods: occupancy-measure-based and policy-based. Our algorithm enjoys an $widetildemathcalO(d sqrtH3 K + sqrtHK(H + barP_K$)$ dynamic regret, where $d$ is the feature dimension.
  arXiv  Detail & Related papers  (2024-11-05T13:55:52Z)
• Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems [10.404992912881601]
  We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions.<n>We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an RL algorithm to learn the optimal policy parameter directly.
  arXiv  Detail & Related papers  (2024-07-24T12:26:21Z)
• The Role of Baselines in Policy Gradient Optimization [83.42050606055822]
  We show that the emphstate value baseline allows on-policy. emphnatural policy gradient (NPG) to converge to a globally optimal. policy at an $O (1/t) rate gradient. We find that the primary effect of the value baseline is to textbfreduce the aggressiveness of the updates rather than their variance.
  arXiv  Detail & Related papers  (2023-01-16T06:28:00Z)
• Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes [80.89852729380425]
  We propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $tilde O(dsqrtH3K)$. Our work provides a complete answer to optimal RL with linear MDPs, and the developed algorithm and theoretical tools may be of independent interest.
  arXiv  Detail & Related papers  (2022-12-12T18:58:59Z)
• Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design [9.554944575754638]
  We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs) We propose two restart-based algorithms, namely Restart-RSMB and Restart-RSQ, and establish their dynamic regrets. This work offers the first non-asymptotic theoretical analyses for the non-stationary risk-sensitive RL in the literature.
  arXiv  Detail & Related papers  (2022-11-19T22:40:09Z)
• Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm [4.128216503196621]
  We propose an On-policy Model-based Safe Deep RL algorithm in which we learn the transition dynamics of the environment in an online manner. We show that our algorithm is more sample efficient and results in lower cumulative hazard violations as compared to constrained model-free approaches.
  arXiv  Detail & Related papers  (2022-10-14T06:53:02Z)
• A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning [113.75991721607174]
  We introduce an interventional prediction module to estimate the probability of two estimated $hatz_i, hatz_j$ belonging to the same environment. We empirically show that $hatZ$ estimated by our method enjoy less redundant information than previous methods.
  arXiv  Detail & Related papers  (2022-06-09T15:01:36Z)
• Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation [107.54516740713969]
  We study human-in-the-loop reinforcement learning (RL) with trajectory preferences. Instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. We propose the first optimistic model-based algorithm for PbRL with general function approximation.
  arXiv  Detail & Related papers  (2022-05-23T09:03:24Z)
• MDPGT: Momentum-based Decentralized Policy Gradient Tracking [29.22173174168708]
  We propose a momentum-based decentralized policy gradient tracking (MDPGT) for multi-agent reinforcement learning. MDPGT achieves the best available sample complexity of $mathcalO(N-1epsilon-3)$ for converging to an $epsilon-stationary point of the global average of $N$ local performance functions. This outperforms the state-of-the-art sample complexity in decentralized model-free reinforcement learning.
  arXiv  Detail & Related papers  (2021-12-06T06:55:51Z)
• Nonstationary Reinforcement Learning with Linear Function Approximation [19.521419943509784]
  We consider reinforcement learning in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. We first develop an optimistic modification of least-squares value with periodic restart, and bound its dynamic regret when variation budgets are known. We derive the first minimax dynamic regret lower bound for nonstationary linear MDPs and as a byproduct establish a minimax regret lower bound for linear MDPs unsolved by Jin et al.
  arXiv  Detail & Related papers  (2020-10-08T20:07:44Z)
• MOPO: Model-based Offline Policy Optimization [183.6449600580806]
  offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. We show that an existing model-based RL algorithm already produces significant gains in the offline setting. We propose to modify the existing model-based RL methods by applying them with rewards artificially penalized by the uncertainty of the dynamics.
  arXiv  Detail & Related papers  (2020-05-27T08:46:41Z)

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.