Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDifferentiable Trust Region Layers for Deep Reinforcement Learning
119
0
0.0
(
0
)
Added by
Fabian Otto
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is difficult. Hence, many approaches, such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), are based on approximations. Due to those approximations, they violate the constraints or fail to find the optimal solution within the trust region. Moreover, they are difficult to implement, often lack sufficient exploration, and have been shown to depend on seemingly unrelated implementation choices. In this work, we propose differentiable neural network layers to enforce trust regions for deep Gaussian policies via closed-form projections. Unlike existing methods, those layers formalize trust regions for each state individually and can complement existing reinforcement learning algorithms. We derive trust region projections based on the Kullback-Leibler divergence, the Wasserstein L2 distance, and the Frobenius norm for Gaussian distributions. We empirically demonstrate that those projection layers achieve similar or better results than existing methods while being almost agnostic to specific implementation choices. The code is available at https://git.io/Jthb0.
rate research
Read More
Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as financial related problems, many engineering problems treat future rewards equally and prefer a long-run average criterion. In this paper, we study the reinforcement learning problem with the long-run average criterion. Firstly, we develop a unified trust region theory with discounted and average criteria. With the average criterion, a novel performance bound within the trust region is derived with the Perturbation Analysis (PA) theory. Secondly, we propose a practical algorithm named Average Policy Optimization (APO), which improves the value estimation with a novel technique named Average Value Constraint. To the best of our knowledge, our work is the first one to study the trust region approach with the average criterion and it complements the framework of reinforcement learning beyond the discounted criterion. Finally, experiments are conducted in the continuous control environment MuJoCo. In most tasks, APO performs better than the discounted PPO, which demonstrates the effectiveness of our approach.
We consider an Intelligent Reflecting Surface (IRS)-aided multiple-input single-output (MISO) system for downlink transmission. We compare the performance of Deep Reinforcement Learning (DRL) and conventional optimization methods in finding optimal phase shifts of the IRS elements to maximize the user signal-to-noise (SNR) ratio. Furthermore, we evaluate the robustness of these methods to channel impairments and changes in the system. We demonstrate numerically that DRL solutions show more robustness to noisy channels and user mobility.
Non-stationarity is one thorny issue in multi-agent reinforcement learning, which is caused by the policy changes of agents during the learning procedure. Current works to solve this problem have their own limitations in effectiveness and scalability, such as centralized critic and decentralized actor (CCDA), population-based self-play, modeling of others and etc. In this paper, we novelly introduce a $delta$-stationarity measurement to explicitly model the stationarity of a policy sequence, which is theoretically proved to be proportional to the joint policy divergence. However, simple policy factorization like mean-field approximation will mislead to larger policy divergence, which can be considered as trust region decomposition dilemma. We model the joint policy as a general Markov random field and propose a trust region decomposition network based on message passing to estimate the joint policy divergence more accurately. The Multi-Agent Mirror descent policy algorithm with Trust region decomposition, called MAMT, is established with the purpose to satisfy $delta$-stationarity. MAMT can adjust the trust region of the local policies adaptively in an end-to-end manner, thereby approximately constraining the divergence of joint policy to alleviate the non-stationary problem. Our method can bring noticeable and stable performance improvement compared with baselines in coordination tasks of different complexity.
The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $mathcal{S}$ and the action space $mathcal{A}$ are both finite, to obtain a nearly optimal policy with sampling access to a generative model, the minimax optimal sample complexity scales linearly with $|mathcal{S}|times|mathcal{A}|$, which can be prohibitively large when $mathcal{S}$ or $mathcal{A}$ is large. This paper considers a Markov decision process (MDP) that admits a set of state-action features, which can linearly express (or approximate) its probability transition kernel. We show that a model-based approach (resp.$~$Q-learning) provably learns an $varepsilon$-optimal policy (resp.$~$Q-function) with high probability as soon as the sample size exceeds the order of $frac{K}{(1-gamma)^{3}varepsilon^{2}}$ (resp.$~$$frac{K}{(1-gamma)^{4}varepsilon^{2}}$), up to some logarithmic factor. Here $K$ is the feature dimension and $gammain(0,1)$ is the discount factor of the MDP. Both sample complexity bounds are provably tight, and our result for the model-based approach matches the minimax lower bound. Our results show that for arbitrarily large-scale MDP, both the model-based approach and Q-learning are sample-efficient when $K$ is relatively small, and hence the title of this paper.
We introduce RL-DARTS, one of the first applications of Differentiable Architecture Search (DARTS) in reinforcement learning (RL) to search for convolutional cells, applied to the Procgen benchmark. We outline the initial difficulties of applying neural architecture search techniques in RL, and demonstrate that by simply replacing the image encoder with a DARTS supernet, our search method is sample-efficient, requires minimal extra compute resources, and is also compatible with off-policy and on-policy RL algorithms, needing only minor changes in preexisting code. Surprisingly, we find that the supernet can be used as an actor for inference to generate replay data in standard RL training loops, and thus train end-to-end. Throughout this training process, we show that the supernet gradually learns better cells, leading to alternative architectures which can be highly competitive against manually designed policies, but also verify previous design choices for RL policies.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
