https://koulanurag.dev/publication/2025-10-20T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/specagent-a-speculative-retrieval-and-forecasting-agent-for-code-completion/2025-10-20T00:00:00+00:00weeklyhttps://koulanurag.dev/event/2024-05-23T12:00:00+00:00weeklyhttps://koulanurag.dev/talk/tea-talk-towards-efficient-representation-and-future-context-transformers-for-goal-conditioned-planning/2024-05-23T12:00:00+00:00weeklyhttps://koulanurag.dev/talk/explaining-rl-agents-from-the-lens-of-perception-memory-and-uncertainties./2024-02-27T16:00:00+00:00weeklyhttps://koulanurag.dev/tag/goal-conditioned-rl/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/maze/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/project/maze-world/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/planning/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/project/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/reinforcement-learning/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/tags/2024-02-19T00:00:00+00:00weeklyhttps://koulanurag.dev/research-directions/foundation-model-for-sdm/2024-02-01T00:00:00+00:00weeklyhttps://koulanurag.dev/research-directions/llm-for-planning/2024-02-01T00:00:00+00:00weeklyhttps://koulanurag.dev/research-directions/2024-02-01T00:00:00+00:00weeklyhttps://koulanurag.dev/research-directions/backward-planning-for-credit-assignment/2024-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication-type/conference/2024-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/pclast-discovering-plannable-continuous-latent-states/2024-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication_types/2024-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/notebooks/brief-on-information-theory/2023-11-20T16:00:00+00:00weeklyhttps://koulanurag.dev/notebooks/2023-11-20T16:00:00+00:00weeklyhttps://koulanurag.dev/2022-10-24T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/offline-policy-comparison-with-confidence-benchmarks-and-baselines/2022-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication-type/workshop/2022-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/control/2021-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/offline-reinforcement-learning/2021-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/tag/robotics/2021-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/project/towards-real-world-rl/2021-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/re-understanding-finite-state-representations-of-recurrent-policy-networks/2021-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/project/learning-n-step-actions-for-control-tasks/2020-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/project/learning-discrete-dynaimcs-for-planning/2020-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/dream-and-search-to-control-latent-space-planning-for-continuous-control/2020-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/research-directions/planning-in-combinatorial-problems/2019-07-12T00:00:00+00:00weeklyhttps://koulanurag.dev/project/ma-gym/2019-04-27T00:00:00+00:00weeklyhttps://koulanurag.dev/slides/quotes/2019-02-05T00:00:00+00:00weeklyhttps://koulanurag.dev/slides/2019-02-05T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/explainable-reinforcement-learning-via-reward-decomposition/2019-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/explaining-deep-adaptive-programs-via-reward-decomposition/2018-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/learning-finite-state-representations-of-recurrent-policy-networks/2018-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/publication/visualizing-and-understanding-atari-agents/2017-01-01T00:00:00+00:00weeklyhttps://koulanurag.dev/categories/weekly