Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Q-Learning Performance on the CartPole Environment Under Observation Noise and Reward Variants
This paper evaluates Q-learning performance in the CartPole reinforcement learning environment under varying levels of observation noise and two distinct reward functions, in the broader context of designing robust learning-based controllers for cyber-physical systems. Specifically, we compare the standard step based reward with a cosine-based reward designed to encourage upright pole balance. Observation noise is modeled as Gaussian noise, with standard deviations scaled to the range of each observation variable. Through multiple training runs at different noise levels, we evaluated convergence behavior, pole angle stability, and cumulative rewards. Our results show that observation noise significantly impairs learning under standard reward, whereas cosine-based reward improves robustness and promotes more stable policies. By linking reinforcement learning with noise-robust control design, this work directly contributes to the understanding of Q-learning under noisy environments and represents a step toward applying reinforcement learning to real-world cyberphysical systems, where noise and variability are inherent.  more » « less
Award ID(s):
2417608 2234911 2209637 2131228 2100134
PAR ID:
10680686
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
Courtesy of IARIA Board and IARIA Press
Date Published:
ISBN:
978-1-68558-316-3
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's interaction with the environment. We study the full class of online manipulation attacks, which include (i) state attacks, (ii) observation attacks (which are a generalization of perceived-state attacks), (iii) action attacks, and (iv) reward attacks. We show the attacker's problem of designing a stealthy attack that maximizes its own expected reward, which often corresponds to minimizing the victim's value, is captured by a Markov Decision Process (MDP) that we call a meta-MDP since it is not the true environment but a higher level environment induced by the attacked interaction. We show that the attacker can derive optimal attacks by planning in polynomial time or learning with polynomial sample complexity using standard RL techniques. We argue that the optimal defense policy for the victim can be computed as the solution to a stochastic Stackelberg game, which can be further simplified into a partially-observable turn-based stochastic game (POTBSG). Neither the attacker nor the victim would benefit from deviating from their respective optimal policies, thus such solutions are truly robust. Although the defense problem is NP-hard, we show that optimal Markovian defenses can be computed (learned) in polynomial time (sample complexity) in many scenarios. 
    more » « less
  2. ; ; ; ; ; (, 2026 65th IEEE Conference on Decision and Control (CDC).)
    We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory. This setting is motivated by safety-critical applications in which a single large violation can be catastrophic and therefore cannot be adequately captured by the standard CMDP framework based on expected cumulative cost. Existing reachability-constrained RL methods adopt Lagrangian-based approaches, yet the underlying duality properties of peakcost constrained MDPs remain unclear. We show that, unlike standard CMDPs, peak-cost constrained MDPs may not admit zero duality gap. We further consider a robust formulation to address simulator-to-real-world mismatch in the transition dynamics. To solve this problem, we develop a surrogate optimization framework and a robust value estimation method based on integral probability metrics. We prove that, with appropriate hyperparameter choices, the surrogate solution attains the same robust reward value as the original problem while violating the constraint by at most ϵ. Experiments show that the proposed method effectively enforces safety under dynamics perturbations while retaining strong reward performance. 
    more » « less
  3. ; (, PLOS Computational Biology)
    Cai, Ming Bo (Ed.)
    A major advance in understanding learning behavior stems from experiments showing that reward learning requires dopamine inputs to striatal neurons and arises from synaptic plasticity of cortico-striatal synapses. Numerous reinforcement learning models mimic this dopamine-dependent synaptic plasticity by using the reward prediction error, which resembles dopamine neuron firing, to learn the best action in response to a set of cues. Though these models can explain many facets of behavior, reproducing some types of goal-directed behavior, such as renewal and reversal, require additional model components. Here we present a reinforcement learning model, TD2Q, which better corresponds to the basal ganglia with two Q matrices, one representing direct pathway neurons (G) and another representing indirect pathway neurons (N). Unlike previous two-Q architectures, a novel and critical aspect of TD2Q is to update the G and N matrices utilizing the temporal difference reward prediction error. A best action is selected for N and G using a softmax with a reward-dependent adaptive exploration parameter, and then differences are resolved using a second selection step applied to the two action probabilities. The model is tested on a range of multi-step tasks including extinction, renewal, discrimination; switching reward probability learning; and sequence learning. Simulations show that TD2Q produces behaviors similar to rodents in choice and sequence learning tasks, and that use of the temporal difference reward prediction error is required to learn multi-step tasks. Blocking the update rule on the N matrix blocks discrimination learning, as observed experimentally. Performance in the sequence learning task is dramatically improved with two matrices. These results suggest that including additional aspects of basal ganglia physiology can improve the performance of reinforcement learning models, better reproduce animal behaviors, and provide insight as to the role of direct- and indirect-pathway striatal neurons. 
    more » « less
  4. ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    In many practical reinforcement learning tasks, feedback is only provided at the end of a long horizon, leading to sparse and delayed rewards. Existing reward redistribution methods typically assume that per-step rewards are independent, thus overlooking interdependencies among state–action pairs. In this paper, we propose a Gaussian Process-based Likelihood Reward Redistribution (GP-LRR) framework that addresses this issue by modeling the reward function as a sample from a Gaussian Process (GP), which explicitly captures dependencies between state–action pairs through the kernel function. By maximizing the likelihood of the observed episodic return via a leave-one-out strategy that leverages the entire trajectory, our framework inherently introduces uncertainty regularization. Moreover, we show that the conventional mean squared error (MSE)-based reward redistribution arises as a special case of our GP-LRR framework when using a degenerate kernel without observation noise. When integrated with an off-policy algorithm such as Soft Actor-Critic, GP-LRR yields dense and informative reward signals, resulting in superior sample efficiency and policy performance on several MuJoCo benchmarks. 
    more » « less
  5. ; ; ; ; (, Advances in neural information processing systems)
    Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent’s inputs, which raises concerns about deploying such agents in the real world. To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against lp-norm bounded adversarial attacks. Our framework is compatible with popular deep reinforcement learning algorithms and we demonstrate its performance with deep Q-learning, A3C and PPO. We experiment on three deep RL benchmarks (Atari, MuJoCo and ProcGen) to show the effectiveness of our robust training algorithm. Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method called Greedy Worst-Case Reward (GWC) to measure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks. All code used for our experiments is available at https://github.com/tuomaso/radial_rl_v2. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email