Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

• URL: http://arxiv.org/abs/2304.12289v1
• Date: Mon, 24 Apr 2023 17:35:47 GMT
• Title: Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
• Authors: Kuo-Hao Zeng, Luca Weihs, Roozbeh Mottaghi, Ali Farhadi
• Abstract summary: We propose to model the impact of actions on-the-fly using latent embeddings. By combining these latent action embeddings with a novel, transformer-based, policy head, we design an Action Adaptive Policy. We show that our AAP is highly performant even when faced, at inference-time with missing actions and, previously unseen, perturbed action space.
• Score: 57.671493865825255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A common assumption when training embodied agents is that the impact of taking an action is stable; for instance, executing the "move ahead" action will always move the agent forward by a fixed distance, perhaps with some small amount of actuator-induced noise. This assumption is limiting; an agent may encounter settings that dramatically alter the impact of actions: a move ahead action on a wet floor may send the agent twice as far as it expects and using the same action with a broken wheel might transform the expected translation into a rotation. Instead of relying that the impact of an action stably reflects its pre-defined semantic meaning, we propose to model the impact of actions on-the-fly using latent embeddings. By combining these latent action embeddings with a novel, transformer-based, policy head, we design an Action Adaptive Policy (AAP). We evaluate our AAP on two challenging visual navigation tasks in the AI2-THOR and Habitat environments and show that our AAP is highly performant even when faced, at inference-time with missing actions and, previously unseen, perturbed action space. Moreover, we observe significant improvement in robustness against these actions when evaluating in real-world scenarios.

Related papers

• Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents [15.902536100207852]
  We propose to consider the consequence of taken actions by CAPEAM in a sequence of actions. We empirically show that the agent with the proposed CAPEAM achieves state-of-the-art performance in various metrics.
  arXiv  Detail & Related papers  (2023-08-14T16:23:21Z)
• Action Sensitivity Learning for Temporal Action Localization [35.65086250175736]
  We propose an Action Sensitivity Learning framework (ASL) to tackle the task of temporal action localization. We first introduce a lightweight Action Sensitivity Evaluator to learn the action sensitivity at the class level and instance level, respectively. Based on the action sensitivity of each frame, we design an Action Sensitive Contrastive Loss to enhance features, where the action-aware frames are sampled as positive pairs to push away the action-irrelevant frames.
  arXiv  Detail & Related papers  (2023-05-25T04:19:14Z)
• Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark [49.58762201363483]
  We introduce RatPose, a bio-robot motion prediction dataset constructed by considering the influence factors of individuals and environments. We propose a Dual-stream Motion-Scenario Decoupling framework that effectively separates scenario-oriented and motion-oriented features. We demonstrate significant performance improvements of the proposed textitDMSD framework on different difficulty-level tasks.
  arXiv  Detail & Related papers  (2023-05-17T14:14:31Z)
• Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint [83.36913240873236]
  Weakly Supervised Temporal Action localization (WTAL) aims to classify and localize temporal boundaries of actions for the video. We propose a simple yet efficient method, named bidirectional semantic consistency constraint (Bi- SCC) to discriminate the positive actions from co-scene actions. Experimental results show that our approach outperforms the state-of-the-art methods on THUMOS14 and ActivityNet.
  arXiv  Detail & Related papers  (2023-04-25T07:20:33Z)
• Leveraging Self-Supervised Training for Unintentional Action Recognition [82.19777933440143]
  We seek to identify the points in videos where the actions transition from intentional to unintentional. We propose a multi-stage framework that exploits inherent biases such as motion speed, motion direction, and order to recognize unintentional actions.
  arXiv  Detail & Related papers  (2022-09-23T21:36:36Z)
• Game-theoretic Objective Space Planning [4.989480853499916]
  Understanding intent of other agents is crucial to deploying autonomous systems in adversarial multi-agent environments. Current approaches either oversimplify the discretization of the action space of agents or fail to recognize the long-term effect of actions and become myopic. We propose a novel dimension reduction method that encapsulates diverse agent behaviors while conserving the continuity of agent actions.
  arXiv  Detail & Related papers  (2022-09-16T07:35:20Z)
• Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction [81.94175022575966]
  We introduce the task of action-driven human motion prediction. It aims to predict multiple plausible future motions given a sequence of action labels and a short motion history.
  arXiv  Detail & Related papers  (2022-05-31T08:38:07Z)
• How RL Agents Behave When Their Actions Are Modified [0.0]
  Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. We present the Modified-Action Markov Decision Process, an extension of the MDP model that allows actions to differ from the policy.
  arXiv  Detail & Related papers  (2021-02-15T18:10:03Z)
• Instance-Aware Predictive Navigation in Multi-Agent Environments [93.15055834395304]
  We propose an Instance-Aware Predictive Control (IPC) approach, which forecasts interactions between agents as well as future scene structures. We adopt a novel multi-instance event prediction module to estimate the possible interaction among agents in the ego-centric view. We design a sequential action sampling strategy to better leverage predicted states on both scene-level and instance-level.
  arXiv  Detail & Related papers  (2021-01-14T22:21:25Z)
• Refined Continuous Control of DDPG Actors via Parametrised Activation [3.32399229114419]
  The proposed method allows the reinforcement learning actor to produce more robust actions that accommodate the discrepancy in the actuators' response functions. This is particularly useful for real life scenarios where actuators exhibit different response functions depending on the load and the interaction with the environment.
  arXiv  Detail & Related papers  (2020-06-04T12:27:46Z)

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.