Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe

• URL: http://arxiv.org/abs/2605.11469v1
• Date: Tue, 12 May 2026 03:33:34 GMT
• Title: Robust Multi-Agent Path Finding under Observation Attacks: A Principled Adversarial-Plus-Smoothing Training Recipe
• Abstract summary: We present two training recipes that keep the same network and the same deployment loop, yet make the policy hold up under perturbed observations.<n>The first recipe, Adv-PPO, trains the shared policy against worst-case perturbations of its own input and selects the checkpoint by performance under adversarial perturbation.<n>The second recipe, Adv-PPO+MACER, fine-tunes that checkpoint with a small on-policy smoothness term whose gradient follows the certified radius of randomized smoothing.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decentralized multi-agent path finding (MAPF) routes a team of agents on a shared grid, each acting from its own local view. The standard solution trains one shared neural policy with Proximal Policy Optimization (PPO), a popular on-policy reinforcement learning algorithm. Such a policy works well on clean observations, but a small input perturbation on one agent often changes its action, which then blocks a neighbour, and the team jams. In this paper we present two training recipes that keep the same network and the same deployment loop, yet make the policy hold up under perturbed observations. The first recipe, Adv-PPO, trains the shared policy against worst-case perturbations of its own input and selects the checkpoint by performance under adversarial perturbation. The second recipe, Adv-PPO+MACER, fine-tunes that checkpoint with a small on-policy smoothness term whose gradient follows the certified radius of randomized smoothing. On POGEMA with 8x8 maps and four agents, the unprotected PPO policy reaches 95.8% clean success but only 2.5% under the strongest attack. Adv-PPO recovers worst-case success to 59.2% at one percentage point of clean cost. Adv-PPO+MACER recovers it to 77.5% +/- 6.0% across three independent seeds at less than one percentage point of clean cost. We support these numbers with per-attack curves, a certified action-stability sanity check (which measures the smoothed-policy wrapper, not the deployed argmax policy), and side-by-side rollout storyboards that show the failure mode and the fix inside one environment instance.

Related papers

• BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents [10.767742708000897]
  Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic.<n>We show that current agentic variants violate this assumption through a state-action credit mismatch.<n>We introduce BiPACE, a drop-in advantage estimator that fixes both sides without adding a critic, auxiliary loss, or extra rollouts.
  arXiv  Detail & Related papers  (2026-06-24T08:32:42Z)
• When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming [0.0]
  We present an empirical failure-mode study of a compact RLHF pipeline with proximal policy optimization (PPO)<n>We classify matched transitions between checkpoints using the directions of the learned reward, judge scores, and average judge score.<n>A pre-transition logistic model predicts future row-level reward hacking with ROC-AUC 0.821, and row-level analysis finds localized reward hacking that checkpoint averages miss in 3 of 12 settings.
  arXiv  Detail & Related papers  (2026-06-02T06:55:52Z)
• Beyond Mode Collapse: Distribution Matching for Diverse Reasoning [69.88237286885065]
  On-policy reinforcement learning methods like GRPO suffer from mode collapse.<n>We show this stems from reverse KL minimization's mode-seeking behavior.<n>We propose DMPO, which prevents mode collapse through principled approximation of forward KL minimization.
  arXiv  Detail & Related papers  (2026-05-19T07:13:00Z)
• See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection [51.59559387222532]
  Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features generalize better to Out-of-Distribution (OOD)<n>We present $2.4-Patch-Selection (SPS), a simple yet effective approach for learning policies that are more robust, generalizable, and efficient.
  arXiv  Detail & Related papers  (2026-01-15T18:58:33Z)
• Coverage Improvement and Fast Convergence of On-policy Preference Learning [67.36750525893514]
  Online on-policy preference learning algorithms for language model alignment can significantly outperform their offline counterparts.<n>We analyze how the sampling policy's coverage evolves throughout on-policy training.<n>We develop principled on-policy schemes for reward distillation in the general function class setting.
  arXiv  Detail & Related papers  (2026-01-13T10:46:06Z)
• PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization [15.965340493880701]
  We introduce Process Relative Policy Optimization (PRPO), which combines outcome reliability with process-level guidance in a critic-free framework.<n>PRPO segments reasoning sequences based on semantic clues, normalizes PRM scores into token-level advantages, and aligns their distribution with outcome advantages.<n>On MATH500, PRPO improves Qwen2.5-Math-1.5B accuracy from 61.2% to 64.4% over GRPO using only eight rollouts and no value network.
  arXiv  Detail & Related papers  (2026-01-12T04:04:43Z)
• A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation [2.5291809836356998]
  We introduce a proximal policy to decouple the off-policy corrections from the controlling policy updates.<n>The policy requires an extra forward pass through the network at each training step, creating a computational bottleneck.<n>We observe that since the proximal policy only serves as a trust region anchor between the behavior and target policies, we can approximate it through simple without explicit computation.
  arXiv  Detail & Related papers  (2025-12-06T19:37:39Z)
• 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)
• Joint action loss for proximal policy optimization [0.0]
  PPO is a state-of-the-art policy gradient algorithm that has been successfully applied to complex computer games such as Dota 2 and Honor of Kings. We propose a multi-action mixed loss that combines joint and separate probabilities. Our hybrid model improves performance by more than 50% in different MuJoCo environments compared to OpenAI's PPO benchmark results.
  arXiv  Detail & Related papers  (2023-01-26T03:42:29Z)
• You May Not Need Ratio Clipping in PPO [117.03368180633463]
  Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. We show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.
  arXiv  Detail & Related papers  (2022-01-31T20:26:56Z)
• The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games [67.47961797770249]
  Multi-Agent PPO (MAPPO) is a multi-agent PPO variant which adopts a centralized value function. We show that MAPPO achieves performance comparable to the state-of-the-art in three popular multi-agent testbeds.
  arXiv  Detail & Related papers  (2021-03-02T18:59:56Z)
• Multi-Agent Trust Region Policy Optimization [34.91180300856614]
  We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. We propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO)
  arXiv  Detail & Related papers  (2020-10-15T17:49:47Z)
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations [88.94162416324505]
  A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks.
  arXiv  Detail & Related papers  (2020-03-19T17:59:59Z)

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.