Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 8 of 8 for “"OpenAI gym"”.

  1. Adversarial Inverse Reinforcement Learning with Noisy Observations

    … problem. Experiments in four benchmark OpenAI Gym environments show that our proposed methods are effective in overcoming demonstration noise for the task of reward learning, but less so for the task of reproducing the expert behavior.</p>

    usm Repository record for Adversarial Inverse Reinforcement Learning with Noisy Observations (opens in a new tab)

  2. Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents

    … related tasks. Empirical results obtained with OpenAI Gym library-based Atari 2600 video gaming environment demonstrate that the proposed hybrid multi-task learning model is successful in addressing key challenges associated with the performance optimization of deep reinforcement learning agents.

    uoit Repository record for Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents (opens in a new tab)

  3. Interpolated Experience Replay for Improved Sample Efficiency of Model-Free Deep Reinforcement Learning Algorithms

    … off-policy reinforcement learning algorithms and OpenAI Gym MuJoCo environments. This improved sample efficiency can enable agents to learn robust and generalizable policies on continuous control tasks in settings where data is limited, such as many real-world robotics tasks.

    mit Repository record for Interpolated Experience Replay for Improved Sample Efficiency of Model-Free Deep Reinforcement Learning Algorithms (opens in a new tab)

  4. Training and Inference in Early-Exit Deep Q-Networks for Efficient Reinforcement Learning

    … environments, we assess the approach on two OpenAI Gym tasks with distinct input regimes: CartPole (vector state) and Atari Pong (pixels). Across both domains, EEDQN yields results that preserve baseline return while lowering expected per-decision FLOPs, with larger savings when many states …

    uic

  5. PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Latent Factor Representation

    … methods and popular benchmark environments from OpenAI Gym and Mujoco, we show that PerSim consistently achieves improved performance, as measured by average reward and prediction error.

    mit Repository record for PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Latent Factor Representation (opens in a new tab)

  6. Ml Controllers With Memory For Robust Quadrotor Control And Research

    … is learned from a pyBullet simulation using the OpenAI Gym framework. Many different training methods and control algorithms are created, tested, and their robustness compared. These methods were all implemented into a real system and their effectiveness compared empirically. The most robust …

    umn Repository record for Ml Controllers With Memory For Robust Quadrotor Control And Research (opens in a new tab)

  7. Accelerare la Realtà: Generazione di Ambienti Virtuali per la Navigazione di Robot in Ambienti Naturali Tramite Deep Learning

    … Engine e un'interfaccia Python compatibile con OpenAI Gym. Esploriamo l'applicazione dell'ambiente di simulazione sviluppato in attività di navigazione nel mondo reale proponendo un nuovo metodo per stimare la traversabilità da input RGB. Dimostriamo l'efficacia di MIDGARD come piattaforma di …

    catania Repository record for Accelerare la Realtà: Generazione di Ambienti Virtuali per la Navigazione di Robot in Ambienti Naturali Tramite Deep Learning (opens in a new tab)

  8. TCP congestion control using reinforcement learning

    TCP, a transport layer protocol which ensures the reliable delivery of information on the network, is the basis of Internet connectivity, with 85% of the worlds Internet traffic being TCP based. TCP however, is slow to adapt to changes in the network, drastically reducing the throughput at the …

    uoit Repository record for TCP congestion control using reinforcement learning (opens in a new tab)