Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic

• URL: http://arxiv.org/abs/2002.05502v2
• Date: Wed, 30 Sep 2020 07:59:32 GMT
• Title: Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic
• Authors: Yangang Ren, Jingliang Duan, Shengbo Eben Li, Yang Guan and Qi Sun
• Abstract summary: This paper introduces the minimax formulation and distributional framework to improve the generalization ability of RL algorithms. We implement our method on the decision-making tasks of autonomous vehicles at intersections and test the trained policy in distinct environments.
• Score: 11.601356612579641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has achieved remarkable performance in numerous sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may not be extended to situations never encountered during training. For practical applications, the randomness of environment usually leads to some devastating events, which should be the focus of safety-critical systems such as autonomous driving. In this paper, we introduce the minimax formulation and distributional framework to improve the generalization ability of RL algorithms and develop the Minimax Distributional Soft Actor-Critic (Minimax DSAC) algorithm. Minimax formulation aims to seek optimal policy considering the most severe variations from environment, in which the protagonist policy maximizes action-value function while the adversary policy tries to minimize it. Distributional framework aims to learn a state-action return distribution, from which we can model the risk of different returns explicitly, thereby formulating a risk-averse protagonist policy and a risk-seeking adversarial policy. We implement our method on the decision-making tasks of autonomous vehicles at intersections and test the trained policy in distinct environments. Results demonstrate that our method can greatly improve the generalization ability of the protagonist agent to different environmental variations.

Related papers

• Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts [0.15889427269227555]
  We develop an adaptive re-training algorithm inspired by evolutionary game theory (EGT) ERPO shows faster policy adaptation, higher average rewards, and reduced computational costs in policy adaptation.
  arXiv  Detail & Related papers  (2024-10-22T09:29:53Z)
• Reparameterized Policy Learning for Multimodal Trajectory Optimization [61.13228961771765]
  We investigate the challenge of parametrizing policies for reinforcement learning in high-dimensional continuous action spaces. We propose a principled framework that models the continuous RL policy as a generative model of optimal trajectories. We present a practical model-based RL method, which leverages the multimodal policy parameterization and learned world model.
  arXiv  Detail & Related papers  (2023-07-20T09:05:46Z)
• CAMEO: Curiosity Augmented Metropolis for Exploratory Optimal Policies [62.39667564455059]
  We consider and study a distribution of optimal policies. In experimental simulations we show that CAMEO indeed obtains policies that all solve classic control problems. We further show that the different policies we sample present different risk profiles, corresponding to interesting practical applications in interpretability.
  arXiv  Detail & Related papers  (2022-05-19T09:48:56Z)
• Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning [3.923354711049903]
  We propose a distributional reinforcement learning framework to learn adaptive policies that can tune their level of conservativity at run-time based on the desired comfort and utility. We show that our algorithm learns policies that can still drive reliable when the perception noise is two times higher than the training configuration for automated merging and crossing at occluded intersections.
  arXiv  Detail & Related papers  (2021-07-15T13:36:55Z)
• Policy Gradient Bayesian Robust Optimization for Imitation Learning [49.881386773269746]
  We derive a novel policy gradient-style robust optimization approach, PG-BROIL, to balance expected performance and risk. Results suggest PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse.
  arXiv  Detail & Related papers  (2021-06-11T16:49:15Z)
• DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies [116.12670064963625]
  We develop an off-policy algorithm called distribution-conditioned reinforcement learning (DisCo RL) to efficiently learn contextual policies. We evaluate DisCo RL on a variety of robot manipulation tasks and find that it significantly outperforms prior methods on tasks that require generalization to new goal distributions.
  arXiv  Detail & Related papers  (2021-04-23T16:51:58Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)
• Bayesian Robust Optimization for Imitation Learning [34.40385583372232]
  Inverse reinforcement learning can enable generalization to new states by learning a parameterized reward function. Existing safe imitation learning approaches based on IRL deal with this uncertainty using a maxmin framework. BROIL provides a natural way to interpolate between return-maximizing and risk-minimizing behaviors.
  arXiv  Detail & Related papers  (2020-07-24T01:52:11Z)
• Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization [100.72335252255989]
  We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments. We propose a novel algorithm that regularizes the training of an RNN-based policy using informed policies trained to maximize the reward in each task.
  arXiv  Detail & Related papers  (2020-05-06T16:14:48Z)
• Improving Robustness via Risk Averse Distributional Reinforcement Learning [13.467017642143581]
  Robustness is critical when the policies are trained in simulations instead of real world environment. We propose a risk-aware algorithm to learn robust policies in order to bridge the gap between simulation training and real-world implementation.
  arXiv  Detail & Related papers  (2020-05-01T20:03:10Z)

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.