New approach learns walk and trot gaits from simulated quadruped using strategic exploration.
problem Learning symmetric gaits (walk and trot) from high-dimensional action spaces.
method Introduced symmetry properties into initial covariance of Gaussian search distribution for strategic exploration. Used episode-based likelihood ratio policy gradient and relative entropy policy search.
result Significant performance enhancement in learning walk and trot gaits compared to random gaits.
CARL controls a quadruped to move naturally in complex environments.
problem Motion synthesis in dynamic environments with complex constraints.
method CARL uses GANs to adapt high-level controls to action distributions and deep reinforcement learning for dynamic recovery.
result CARL can be controlled with high-level directives and react naturally to dynamic environments.
GRAM enhances deep RL for reliable real-world deployment.
problem Generalizing deep RL across in-distribution and out-of-distribution scenarios.
method Introduces a robust adaptation module and a joint training pipeline.
result GRAM achieves strong generalization performance in simulations and hardware.
Robots learn to navigate rough terrain using reinforcement learning.
problem Generalizing robot behavior to new, unseen rough terrains.
method PPMC RL Training Algorithm
result Robots achieve 100% success rate in learning new rough terrain maps.
The paper develops a learning framework for diverse legged robots.
problem General and autonomous learning of core skills in locomotion.
method Data-efficient, off-policy multi-task RL algorithm with semantically identical reward functions.
result The same algorithm can learn diverse and reusable locomotion skills across different legged robots.
Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics. However, it is well known that DFO methods suffer from proh…
Symmetry augmentation speeds up learning in robotics tasks.
problem Learning efficiency in robotics tasks with limited data.
method Data augmentation using symmetry in the quadruped domain of DeepMind control suite.
result Agent learns faster with augmented symmetry experiences.
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that facilitates this goal remains a significant challenge. We approach this challenge us…
New method improves smoothness of robot learning.
problem Jerky motion patterns on real robots from Deep RL exploration.
method Adapting state-dependent exploration to Deep RL algorithms with gSDE.
result Improved exploration and performance on real robots.
Paper introduces new motion synthesis model using normalizing flows.
problem Data-driven motion synthesis with probabilistic and controllable models.
method Probabilistic, generative, autoregressive model using normalizing flows and LSTMs.
result Randomly sampled motion from the model outperforms task-agnostic baselines.
Deep learning enables a robot to navigate autonomously within a perimeter.
problem Autonomous path planning for space exploration robots.
method Deep reinforcement learning with randomized reward function parameters.
result Trained robot can navigate to any point within a perimeter without prior knowledge.
Unified policy controls diverse agents through modular neural networks.
problem Learning control policies for various agent morphologies.
method Shared Modular Policies (SMP) with decentralized control and message passing.
result A single modular policy controls multiple agent morphologies.
Director learns hierarchical behaviors from pixels, outperforming exploration methods.
problem Challenges in learning long-term hierarchical behaviors from pixels.
method Directly learns hierarchical behaviors from pixels using a latent space world model.
result Director outperforms exploration methods on various tasks.
Robots' agility in changing terrain helps financial models adapt to market shifts.
problem Challenges in financial market forecasting due to regime switching.
method Adapts pretrained LLMs using intrinsic market rewards and reinforcement learning.
result Significantly improved accuracy in adapting to market regime shifts.