Vitaly Levdik

Arash Tavakoli, Vitaly Levdik, Riashat Islam et al.

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a more diverse set of initial states, as well as allowing it to restart in states associated with significant past experiences. This approach is compatible with both on-policy and off-policy methods. However, a caveat is that altering the distribution of initial states could change the optimal policies when searching within a restricted class of policies. To reduce this unsought learning bias, we evaluate our approach in deep reinforcement learning which benefits from the high representational capacity of deep neural networks. We instantiate three variants of our approach, each inspired by an idea in the context of experience replay. Using these variants, we show that performance gains can be achieved, especially in hard exploration problems.

Fabio Pardo, Vitaly Levdik, Petar Kormushev

Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However the expensive numerous updates in parallel limited the approach to small tabular cases so far. To tackle this problem we propose to use convolutional network architectures to generate Q-values and updates for a large number of goals at once. We demonstrate the accuracy and generalization qualities of the proposed method on randomly generated mazes and Sokoban puzzles. In the case of on-screen goal coordinates the resulting mapping from frames to distance-maps directly informs the agent about which places are reachable and in how many steps. As an example of application we show that replacing the random actions in epsilon-greedy exploration by several actions towards feasible goals generates better exploratory trajectories on Montezuma's Revenge and Super Mario All-Stars games.

Fabio Pardo, Vitaly Levdik, Petar Kormushev

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace single random action choices by random goals selection followed by several steps in their direction. This approach is compatible with any curiosity-based exploration and off-policy reinforcement learning agents and generates longer and safer trajectories than individual random actions. To illustrate this, we present a task-independent agent that learns to reach coordinates in screen frames and demonstrate its ability to explore with the game Super Mario Bros. improving significantly the score of a baseline DQN agent.

Fabio Pardo, Arash Tavakoli, Vitaly Levdik et al.

In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent's input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning. We argue that this insight should be incorporated by bootstrapping from the value of the state at the end of each partial episode. For both cases, we illustrate empirically the significance of our considerations in improving the performance and stability of existing reinforcement learning algorithms, showing state-of-the-art results on several control tasks.