Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

• URL: http://arxiv.org/abs/2304.13424v1
• Date: Wed, 26 Apr 2023 10:12:12 GMT
• Title: Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
• Abstract summary: We show the prevalence of emphgeneralization failure on controllable states from stranger agents. We propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training.
• Score: 88.08381083207449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we define, evaluate, and improve the ``relay-generalization'' performance of reinforcement learning (RL) agents on the out-of-distribution ``controllable'' states. Ideally, an RL agent that generally masters a task should reach its goal starting from any controllable state of the environment instead of memorizing a small set of trajectories. For example, a self-driving system should be able to take over the control from humans in the middle of driving and must continue to drive the car safely. To practically evaluate this type of generalization, we start the test agent from the middle of other independently well-trained \emph{stranger} agents' trajectories. With extensive experimental evaluation, we show the prevalence of \emph{generalization failure} on controllable states from stranger agents. For example, in the Humanoid environment, we observed that a well-trained Proximal Policy Optimization (PPO) agent, with only 3.9\% failure rate during regular testing, failed on 81.6\% of the states generated by well-trained stranger PPO agents. To improve "relay generalization," we propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training. After applying STA to the Soft Actor Critic's (SAC) training procedure, we reduced the failure rate of SAC under relay-evaluation by more than three times in most settings without impacting agent performance and increasing the needed number of environment interactions. Our code is available at https://github.com/lan-lc/STA.

Related papers

• RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback [54.39884046754265]
  RetroAgent is an online RL framework that enables agents to master complex interactive environments.<n>Our experiments show that RetroAgent achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-03-09T16:23:33Z)
• A Rubric-Supervised Critic from Sparse Real-World Outcomes [87.11204512676193]
  Real-world coding agents operate with humans in the loop, where success signals are typically noisy, delayed, and sparse.<n>We propose a process to learn a "critic" model from sparse and noisy interaction data, which can then be used both as a reward model for either RL-based training or inference-time scaling.
  arXiv  Detail & Related papers  (2026-03-04T07:23:54Z)
• Accelerating Robotic Reinforcement Learning with Agent Guidance [17.75786047468276]
  Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error.<n>Recent Human-in-the-Loop (HIL) methods accelerate training by using human corrections, yet this approach faces a scalability barrier.<n>We present Agent-guided Policy Search (AGPS), a framework that automates the training pipeline by replacing human supervisors with a multimodal agent.
  arXiv  Detail & Related papers  (2026-02-12T14:09:32Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learning [11.602831593017427]
  This paper addresses the challenges of training end-to-end autonomous driving agents using Reinforcement Learning (RL)<n>RL agents are typically trained in a fixed set of scenarios and nominal behavior of surrounding road users in simulations.<n>We propose an automatic curriculum learning framework that dynamically generates driving scenarios with adaptive complexity based on the agent's evolving capabilities.
  arXiv  Detail & Related papers  (2025-05-13T06:26:57Z)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.65034908728828]
  Training large language models (LLMs) as interactive agents presents unique challenges. While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored. We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• AgentRefine: Enhancing Agent Generalization through Refinement Tuning [28.24897427451803]
  Large Language Model (LLM) based agents have proved their ability to perform complex tasks like humans. There is still a large gap between open-sourced LLMs and commercial models like the GPT series. In this paper, we focus on improving the agent generalization capabilities of LLMs via instruction tuning.
  arXiv  Detail & Related papers  (2025-01-03T08:55:19Z)
• Human-compatible driving partners through data-regularized self-play reinforcement learning [3.9682126792844583]
  Human-Regularized PPO (HR-PPO) is a multi-agent algorithm where agents are trained through self-play with a small penalty for deviating from a human reference policy. Results show our HR-PPO agents are highly effective in achieving goals, with a success rate of 93%, an off-road rate of 3.5%, and a collision rate of 3%.
  arXiv  Detail & Related papers  (2024-03-28T17:56:56Z)
• ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy [47.42940885853956]
  A$3$T is a framework that enables the Autonomous. of Agent Trajectories in the style of ReAct. In AlfWorld, the agent trained with A$3$T obtains a 1-shot success rate of 96%, and 100% success with 4 iterative rounds.
  arXiv  Detail & Related papers  (2024-03-21T17:43:44Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world. Recent methods aim to mitigate misalignment by learning reward functions from human preferences. We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Explaining Reinforcement Learning Policies through Counterfactual Trajectories [147.7246109100945]
  A human developer must validate that an RL agent will perform well at test-time. Our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.
  arXiv  Detail & Related papers  (2022-01-29T00:52:37Z)
• Explore and Control with Adversarial Surprise [78.41972292110967]
  Reinforcement learning (RL) provides a framework for learning goal-directed policies given user-specified rewards. We propose a new unsupervised RL technique based on an adversarial game which pits two policies against each other to compete over the amount of surprise an RL agent experiences. We show that our method leads to the emergence of complex skills by exhibiting clear phase transitions.
  arXiv  Detail & Related papers  (2021-07-12T17:58:40Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)
• Automatic Data Augmentation for Generalization in Deep Reinforcement Learning [39.477038093585726]
  Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios. Data augmentation has recently been shown to improve the sample efficiency and generalization of RL agents. We show that our agent learns policies and representations that are more robust to changes in the environment that do not affect the agent.
  arXiv  Detail & Related papers  (2020-06-23T09:50:22Z)
• Safe Reinforcement Learning via Curriculum Induction [94.67835258431202]
  In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. Existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor.
  arXiv  Detail & Related papers  (2020-06-22T10:48:17Z)

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.